© 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. 107776
    Prev
    Next
    INDEX
    Explanations

    you

    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
    à¸Ĭา
    -0.30
    èķĥ
    -0.26
    æ©Ļ
    -0.26
    æ¶Īéĺ²
    -0.25
    aret
    -0.25
    ãģ¡ãĤĥãĤĵãģ¨
    -0.24
    æĭ¿äºĨ
    -0.24
    InputChange
    -0.23
    abeth
    -0.23
    ogue
    -0.23
    POSITIVE LOGITS
    æ±
    0.31
    çIJĨ解
    0.29
    LEG
    0.28
    çģ«åĬĽ
    0.27
     understanding
    0.27
    çļĦçIJĨ解
    0.26
     ultimate
    0.26
    iman
    0.26
    GS
    0.26
     planning
    0.25
    Activations Density 0.967%

    No Known Activations