© 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. 108410
    Prev
    Next
    INDEX
    Explanations

    contribution

    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
    äºĨä¸Ģ声
    -0.29
     Impress
    -0.27
    ijIJ
    -0.27
    åħ·æľīä¸Ģå®ļ
    -0.26
    ÑģÑı
    -0.26
    æ³ģ
    -0.26
    ãģĹãģŁãĤĤãģ®
    -0.26
    icularly
    -0.26
    ably
    -0.25
    ä¸Ģå®ļç¨ĭ度
    -0.25
    POSITIVE LOGITS
    /configuration
    0.29
    ate
    0.28
    ality
    0.27
    ele
    0.27
     made
    0.26
    æĵİ
    0.26
     to
    0.25
    æĢª
    0.25
     of
    0.25
    ãģıãĤĬ
    0.24
    Activations Density 0.198%

    No Known Activations