© 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. 27-TRANSCODER-HP
    7. 57760
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Column
    -0.27
    desired
    -0.25
     enjoys
    -0.25
     Ñģобой
    -0.25
    inya
    -0.25
    模仿
    -0.24
    èĢ¦
    -0.24
    esto
    -0.24
     Ge
    -0.24
    omo
    -0.24
    POSITIVE LOGITS
    缸æ¯Ķä¹ĭä¸ĭ
    0.28
    羣æŃ£
    0.26
    éĤ£ç§į
    0.26
    æ¼Ķ
    0.25
    çĽĬ
    0.25
    å¯Ĵåģĩ
    0.25
    &view
    0.24
    æķĻåѦ
    0.24
    éĤ£ä½ł
    0.24
    ald
    0.23
    Activations Density 0.033%

    No Known Activations