© 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. 40327
    Prev
    Next
    INDEX
    Explanations

    Jim

    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
     é»
    -0.30
     à¸Ļาย
    -0.27
    è´¢æĶ¿éĥ¨
    -0.25
    è²Ĥ
    -0.24
    -Ray
    -0.24
     à¸ŀ
    -0.24
    redni
    -0.24
     Hay
    -0.23
    ìĸij
    -0.23
    ']}'
    -0.23
    POSITIVE LOGITS
     helicopt
    0.31
     franca
    0.30
    ans
    0.28
    ANS
    0.27
    Above
    0.26
    æIJŃæ¡£
    0.26
     fla
    0.26
     meme
    0.26
     spread
    0.25
    uset
    0.25
    Activations Density 8.434%

    No Known Activations