© 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. 108394
    Prev
    Next
    INDEX
    Explanations

    ecological systems

    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¸įçĶĺ
    -0.30
    CPP
    -0.28
    ä¼ģä¸ļæıIJä¾Ľ
    -0.27
    æŀľèĶ¬
    -0.27
    æ¶Ĥ
    -0.27
     bites
    -0.26
    èĥ½çľĭåĩº
    -0.26
    äºij端
    -0.25
    çľĭä¸įåĩº
    -0.25
    .colors
    -0.25
    POSITIVE LOGITS
    arcy
    0.30
    ets
    0.28
     performance
    0.26
    sten
    0.25
     MAGIC
    0.25
    ety
    0.24
    ами
    0.24
    è¿ĻæĿ¡è·¯
    0.24
    (policy
    0.24
    管çIJĨ
    0.24
    Activations Density 0.171%

    No Known Activations