© 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. 39688
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    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
    .edu
    -0.26
    èªį
    -0.25
    enth
    -0.25
    åĽĽä¸ª
    -0.25
    便
    -0.25
    port
    -0.25
    ouble
    -0.25
    ä¸ĩ个
    -0.25
    ä½łåĢij
    -0.24
    æºĸåĤĻ
    -0.24
    POSITIVE LOGITS
     affected
    0.29
     distracted
    0.28
     afflicted
    0.26
    åĵŃäºĨ
    0.26
     cps
    0.26
     allegedly
    0.25
     unaffected
    0.25
     falsely
    0.25
     distract
    0.25
    affected
    0.24
    Activations Density 0.107%

    No Known Activations