© 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. 40361
    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
    ITS
    -0.31
    åĩºè·¯
    -0.27
     Rupert
    -0.26
    åħľ
    -0.25
    itage
    -0.25
    |RF
    -0.25
    missions
    -0.25
    çĦķåıij
    -0.25
    ertino
    -0.24
     Cord
    -0.23
    POSITIVE LOGITS
     associ
    0.25
    ¢
    0.25
    \$
    0.25
    puts
    0.24
     perd
    0.24
    ulous
    0.24
    b
    0.23
    ãĤıãģĭãĤĭ
    0.23
     pager
    0.23
     pled
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.