© 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. 108925
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    urable
    -0.28
    TK
    -0.28
    ãģĵãģ¡ãĤī
    -0.27
    ç«Ļ
    -0.26
     same
    -0.26
    isky
    -0.26
    same
    -0.25
    minus
    -0.25
    ä¸įä½ı
    -0.25
    kins
    -0.25
    POSITIVE LOGITS
     sle
    0.27
    rna
    0.26
    ocl
    0.26
    éĻįèĩ³
    0.26
    为人
    0.26
    ernet
    0.25
    angen
    0.24
    ç²²
    0.24
    egie
    0.24
    ([\
    0.24
    Activations Density 0.106%

    No Known Activations