© 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. 39751
    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
     infuri
    -0.27
     gravid
    -0.27
     masturb
    -0.27
     impover
    -0.26
     implic
    -0.25
    XMLElement
    -0.24
     met
    -0.24
     contradiction
    -0.24
     harass
    -0.24
     strugg
    -0.24
    POSITIVE LOGITS
     ê²°
    0.28
     BI
    0.25
    %↵
    0.25
     %↵
    0.24
    åľ°çĤ¹
    0.24
     architecture
    0.24
    eneral
    0.24
    æīĭ段
    0.24
    овÑĭй
    0.24
    itecture
    0.23
    Activations Density 76.737%

    No Known Activations

    This feature has no known activations.