© 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. 40309
    Prev
    Next
    INDEX
    Explanations

    technical/location names

    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
    hort
    -0.33
     Coul
    -0.28
    orts
    -0.28
    tracts
    -0.28
    bery
    -0.27
    vert
    -0.27
    hots
    -0.27
    å¼Ľ
    -0.27
    elli
    -0.27
    hoot
    -0.26
    POSITIVE LOGITS
     handlers
    0.27
    -----------*/↵
    0.26
     encoded
    0.26
    èģĶ
    0.26
    ç¼ĸåı·
    0.25
    è§Ĵ
    0.24
    ä¸Ģåı¥è¯Ŀ
    0.24
    á¿ĸ
    0.24
    è¿Ľå±ķæĥħåĨµ
    0.24
    æ£Ģ
    0.23
    Activations Density 1.113%

    No Known Activations