© 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. 40225
    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
    placeholders
    -0.26
     Philly
    -0.26
    éĵ§
    -0.25
    egree
    -0.25
    çĤ¹å¤´
    -0.24
    åѤç«ĭ
    -0.24
     compliments
    -0.24
    âĺľ
    -0.23
    æ³±
    -0.23
    оÑĢ
    -0.23
    POSITIVE LOGITS
    steen
    0.27
     pub
    0.27
     Prop
    0.27
     press
    0.26
    éĢıæĺİ
    0.26
     Transparent
    0.25
     Pub
    0.25
    nin
    0.24
     Highly
    0.24
    fte
    0.24
    Activations Density 67.096%

    No Known Activations

    This feature has no known activations.