© 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. 39184
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     erh
    -0.27
    STITUTE
    -0.25
    çŀ¥
    -0.24
    naissance
    -0.24
    â
    -0.24
    rait
    -0.23
     paras
    -0.23
    Äĥm
    -0.23
     circum
    -0.23
     cres
    -0.23
    POSITIVE LOGITS
    eding
    0.31
    Sibling
    0.27
    assen
    0.27
    å¼ŁåħĦ
    0.26
    åĪ°æľŁ
    0.26
    ÑįÑĢ
    0.26
    ç»Ħç»ĩé¢Ĩ导
    0.26
    çģ¸
    0.26
    (lang
    0.25
     siblings
    0.25
    Activations Density 85.476%

    No Known Activations