© 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. 35-TRANSCODER-HP
    7. 39132
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stairs
    -0.27
     getHeight
    -0.26
     ÑĥпÑĢав
    -0.24
    ForEach
    -0.24
     Fore
    -0.24
     Mich
    -0.24
     Trot
    -0.24
    jid
    -0.24
    GED
    -0.23
    anka
    -0.23
    POSITIVE LOGITS
     franca
    0.30
    éĢıæĺİ
    0.28
    ç§ĺ
    0.26
     saÄŁlamak
    0.26
     malign
    0.25
     Muslims
    0.25
    åı£å¾Ħ
    0.24
    æĬ¢åħĪ
    0.24
     muslim
    0.24
    uslim
    0.24
    Activations Density 1.333%

    No Known Activations

    This feature has no known activations.