© 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. 57714
    Prev
    Next
    INDEX
    Explanations

    can

    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
    ç»ĻæĤ¨
    -0.25
     alarms
    -0.25
    åĽŀéģ¿
    -0.25
    ãģijãģ¦
    -0.24
     alarm
    -0.24
     needles
    -0.24
    åı¯ä¾Ľ
    -0.24
    ovable
    -0.24
    ç©¿è¡£
    -0.24
    side
    -0.24
    POSITIVE LOGITS
    thon
    0.33
    æĸ
    0.29
     disrupt
    0.29
     poll
    0.29
    æĮ£
    0.28
    çł´åĿı
    0.28
     Poll
    0.27
     pollut
    0.26
     disease
    0.25
     modifies
    0.25
    Activations Density 0.001%

    No Known Activations