© 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. 39500
    Prev
    Next
    INDEX
    Explanations

    Scri

    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
    åıĺåĮĸ
    -0.27
    åŃIJå¼¹
    -0.26
    _deriv
    -0.25
    æį¢äºĨ
    -0.25
    Recursive
    -0.25
    é«ĺæĸ°
    -0.25
    身躯
    -0.24
    çļĦåıĺåĮĸ
    -0.24
    ç¥Ń
    -0.24
    åºĦ
    -0.24
    POSITIVE LOGITS
    5
    0.29
     RDD
    0.28
    aroo
    0.28
    adf
    0.27
    b
    0.27
     Ard
    0.26
    åĶĩ
    0.26
     clutch
    0.26
    brook
    0.26
    6
    0.26
    Activations Density 0.048%

    No Known Activations