© 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. 22-TRANSCODER-HP
    7. 112307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬŀ好
    -0.31
    ErrorException
    -0.26
    gram
    -0.26
     unwilling
    -0.25
    åIJĪæ³ķ
    -0.24
    è£ķ
    -0.24
    Regs
    -0.23
    rtype
    -0.23
    ISTIC
    -0.23
    éĥ½åı¯ä»¥
    -0.23
    POSITIVE LOGITS
    _tau
    0.25
    elihood
    0.25
    è·µ
    0.25
     dead
    0.25
    chia
    0.25
    ippi
    0.25
    csv
    0.25
    vy
    0.25
    rase
    0.25
     Second
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.