© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43496
    Prev
    Next
    INDEX
    Explanations

    color

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beck
    -0.29
    踵
    -0.28
     banker
    -0.27
    æĭ¥
    -0.26
     ----------------------------------------------------------------------------↵
    -0.25
    urga
    -0.25
    beb
    -0.25
    ¶Ī
    -0.25
    uffer
    -0.25
    åĢºæĿĥ人
    -0.24
    POSITIVE LOGITS
     theory
    0.54
     theories
    0.47
     Theory
    0.45
    theory
    0.44
    Theory
    0.44
    çIJĨ论
    0.44
    çIJĨè«ĸ
    0.40
     theorists
    0.39
     THEORY
    0.39
     theoretically
    0.33
    Activations Density 0.002%

    No Known Activations