© 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. 87959
    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
    Difference
    -0.26
     Lon
    -0.25
    è¹Ĭ
    -0.25
    stations
    -0.24
    æ¸ħæĸ°
    -0.24
     DEAD
    -0.23
    ipe
    -0.23
    .sf
    -0.23
     Dead
    -0.23
    Clean
    -0.22
    POSITIVE LOGITS
    ãĥĪãĥ«
    0.26
     stylist
    0.25
     buckle
    0.24
    èĪª
    0.24
     endorsement
    0.23
    getElementsByTagName
    0.23
     memberships
    0.23
    è¾ķ
    0.23
     inconsistency
    0.23
     rainbow
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.