© 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. 33-TRANSCODER-HP
    7. 53140
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼ĢæĿ¥
    -0.27
    angs
    -0.26
    ä¹ĺ客
    -0.26
    åİŁè°ħ
    -0.25
    аниÑİ
    -0.25
    aine
    -0.25
    angling
    -0.24
    头ä¸Ĭ
    -0.23
    ardown
    -0.23
    ĽĦ
    -0.23
    POSITIVE LOGITS
     ik
    0.32
    berg
    0.31
     Ik
    0.30
    ik
    0.30
     ich
    0.28
    ivor
    0.28
    Ik
    0.27
    夫人
    0.26
     thaw
    0.26
    iks
    0.26
    Activations Density 0.248%

    No Known Activations