© 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. 108222
    Prev
    Next
    INDEX
    Explanations

    finance/code

    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
    ä¸Ģ个æĸ°çļĦ
    -0.29
    éĩĬæĶ¾
    -0.28
     Elev
    -0.28
    å²Ľä¸Ĭ
    -0.27
    ä¸Ģ身
    -0.26
    åĪĨæµģ
    -0.26
    Injected
    -0.26
    ç»ıæµİä½ĵ
    -0.26
    Ìģ
    -0.25
    æĶ¾åĩº
    -0.25
    POSITIVE LOGITS
    SCP
    0.27
     noc
    0.27
    erk
    0.26
    åĩ½
    0.26
    utility
    0.25
    Msp
    0.25
    _tools
    0.25
    ç§ij
    0.25
     scn
    0.24
     sorts
    0.24
    Activations Density 0.893%

    No Known Activations