© 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. 108752
    Prev
    Next
    INDEX
    Explanations

    universities/college

    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
    èĦ¸
    -0.31
    roads
    -0.27
     face
    -0.27
    mans
    -0.27
    éĿ¢éĥ¨
    -0.26
    BOTTOM
    -0.26
    åľ°è´¨
    -0.26
    asar
    -0.26
    aron
    -0.25
    acct
    -0.25
    POSITIVE LOGITS
    ories
    0.27
    å·§
    0.26
    æľªæĪIJå¹´
    0.26
    semblies
    0.25
     Desc
    0.24
    _placement
    0.23
    /fontawesome
    0.23
    hon
    0.23
    ughters
    0.23
    iod
    0.23
    Activations Density 0.169%

    No Known Activations