© 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. 43248
    Prev
    Next
    INDEX
    Explanations

    day

    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
    upon
    -0.32
     upon
    -0.32
     Upon
    -0.31
    æ´¸
    -0.28
    ustralian
    -0.27
    illusion
    -0.27
    PIO
    -0.27
    ODB
    -0.27
    Upon
    -0.26
    onium
    -0.26
    POSITIVE LOGITS
    long
    0.58
     long
    0.53
    éķ¿
    0.47
    -long
    0.42
    éķ·
    0.40
     Long
    0.40
    Long
    0.40
    LONG
    0.38
    (long
    0.34
    _long
    0.34
    Activations Density 0.039%

    No Known Activations