© 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. 23-TRANSCODER-HP
    7. 24066
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĵĸ
    -0.27
     Bian
    -0.27
     enclosed
    -0.27
    åħ¥
    -0.27
    Ot
    -0.26
    åĽŁ
    -0.26
    -automatic
    -0.25
    å¹³æĿ¿
    -0.25
     slips
    -0.25
    UA
    -0.25
    POSITIVE LOGITS
    ToStr
    0.29
    ç±´
    0.28
     dicks
    0.27
    actus
    0.26
    iners
    0.26
    ãĥijãĥ¼
    0.25
    ucky
    0.25
    owski
    0.24
    çĸ½
    0.24
     posed
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.