© 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. 25-TRANSCODER-HP
    7. 107686
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯ķä¸ļåIJİ
    -0.29
     irr
    -0.26
    edException
    -0.25
     getDefault
    -0.24
    ooled
    -0.24
    .ov
    -0.24
    /default
    -0.24
     pupils
    -0.24
    .helpers
    -0.23
    psc
    -0.23
    POSITIVE LOGITS
    æݨèįIJéĺħ读
    0.29
    æŁ¥è¯¢
    0.29
    oho
    0.25
    åıĺå½¢
    0.25
    iosity
    0.24
    arium
    0.24
    æŁ¥è©¢
    0.24
    éķĶ
    0.24
    å®ĺæĸ¹å¾®ä¿¡
    0.24
    iment
    0.24
    Activations Density 0.845%

    No Known Activations