© 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. 39381
    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
     Carpet
    -0.23
     —
    -0.23
    HECK
    -0.23
    å¼±
    -0.22
    omers
    -0.21
    ä¸įåĪ°
    -0.21
    ----</
    -0.20
    ãģ£ãģ
    -0.20
    çĻ¾åº¦
    -0.20
    .exist
    -0.20
    POSITIVE LOGITS
    PasswordEncoder
    0.24
    marsh
    0.24
    'h
    0.24
    nex
    0.23
    æ±
    0.23
    æ··åĩĿ
    0.22
    bright
    0.22
    ä¹ŁçŁ¥éģĵ
    0.22
    çĶļèĩ³æĺ¯
    0.22
    é¦ĸåħĪæĺ¯
    0.21
    Activations Density 53.675%

    No Known Activations

    This feature has no known activations.