© 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. 8801
    Prev
    Next
    INDEX
    Explanations

    at

    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
    çĦ¶
    -0.27
    ç¨ĭ
    -0.27
    erie
    -0.27
    aming
    -0.26
    IFY
    -0.26
    åij³
    -0.25
    -shell
    -0.25
    afa
    -0.24
    tor
    -0.23
    èħĶ
    -0.23
    POSITIVE LOGITS
    失åİ»
    0.27
    æ³ķ令
    0.26
    身影
    0.25
    getLast
    0.24
    æ»ŀ
    0.24
    ä¸įåı¯ç¼ºå°ij
    0.24
    .Clamp
    0.24
    çļĦç»ıéªĮ
    0.23
    ---------↵
    0.23
     clearTimeout
    0.23
    Activations Density 0.022%

    No Known Activations