© 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. 108327
    Prev
    Next
    INDEX
    Explanations

    names

    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
    .AP
    -0.26
    essel
    -0.26
    ãģĦãģĨ
    -0.26
    è°ļ
    -0.26
    ä»ħ代表
    -0.24
    ymous
    -0.24
     FU
    -0.24
    ç½ķ
    -0.24
    è¿ĻäºĽä¸ľè¥¿
    -0.23
    letcher
    -0.23
    POSITIVE LOGITS
    blo
    0.28
    oque
    0.28
    éĩİ
    0.27
    agog
    0.26
    otto
    0.25
    avo
    0.25
    ä¸īè§Ĵ
    0.24
     blo
    0.24
     provoc
    0.24
     extremes
    0.24
    Activations Density 0.974%

    No Known Activations