© 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. 108968
    Prev
    Next
    INDEX
    Explanations

    new

    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
    åľ¨çİ°åľº
    -0.29
    Frameworks
    -0.27
     childs
    -0.26
    ujet
    -0.26
     lleg
    -0.25
    èIJ¥åľ°
    -0.25
    è¿ĻäºĽä¸ľè¥¿
    -0.25
    åIJĦ家
    -0.24
    缮åīį为æŃ¢
    -0.24
    å¿ĥå¢ĥ
    -0.24
    POSITIVE LOGITS
     research
    0.35
     affine
    0.29
     data
    0.29
     gesch
    0.26
     affiliate
    0.26
    gent
    0.25
     historical
    0.25
    isor
    0.25
     hardware
    0.25
    ç§ijåѦçłĶ究
    0.25
    Activations Density 0.940%

    No Known Activations