© 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. 108114
    Prev
    Next
    INDEX
    Explanations

    fasc

    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
    ewn
    -0.27
    çľ·
    -0.26
    笨
    -0.26
    è¿ĻæŶåĢĻ
    -0.24
    åĴĸåķ¡
    -0.24
    æݨèįIJéĺħ读
    -0.24
     Legal
    -0.23
    uzzi
    -0.23
    Legal
    -0.23
    unter
    -0.23
    POSITIVE LOGITS
    Æ°Æ¡ng
    0.28
    ilateral
    0.27
    érc
    0.27
    elsius
    0.24
    ific
    0.24
    TOCOL
    0.24
     fancy
    0.23
    аÑĤелÑĮ
    0.23
     themselves
    0.23
    \Context
    0.23
    Activations Density 0.513%

    No Known Activations