© 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. 108154
    Prev
    Next
    INDEX
    Explanations

    fail

    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
    lein
    -0.28
    bff
    -0.25
    .tim
    -0.24
    _accessible
    -0.24
    sein
    -0.24
     Theft
    -0.24
    éĢĨ
    -0.23
    è¡ĮæĶ¿æī§æ³ķ
    -0.23
    çļĦè¯Ŀé¢ĺ
    -0.23
     Berger
    -0.23
    POSITIVE LOGITS
    éĴ®
    0.28
    ////////////////////////////////////////////////////////////////////
    0.28
    aret
    0.26
    秣
    0.25
    人类
    0.25
     sor
    0.25
    VV
    0.24
    纹
    0.24
    çķĻä¸ĭ
    0.24
    Tor
    0.24
    Activations Density 0.154%

    No Known Activations