© 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. 107700
    Prev
    Next
    INDEX
    Explanations

    La

    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
    loy
    -0.31
    ovement
    -0.25
    rules
    -0.25
    hy
    -0.25
    åĬŀäºĭ
    -0.25
     houses
    -0.24
    éĤ£æ®µ
    -0.24
    liable
    -0.24
    æľįåĬ¡æ°´å¹³
    -0.23
    æĪ¿åŃIJ
    -0.23
    POSITIVE LOGITS
    ä¸įè´Ł
    0.27
    ÑĢажа
    0.26
    rne
    0.26
    aho
    0.24
    auge
    0.24
    åº
    0.24
    irsch
    0.23
    IVO
    0.23
    mie
    0.23
    parsers
    0.23
    Activations Density 0.947%

    No Known Activations