© 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. 108841
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    ivor
    -0.26
    orado
    -0.24
     aging
    -0.24
     industry
    -0.24
    antry
    -0.24
     automobile
    -0.24
     exploitation
    -0.24
     elabor
    -0.24
    beit
    -0.24
    -taking
    -0.23
    POSITIVE LOGITS
     nämlich
    0.26
    ä¸ĥ大
    0.25
    åıªèĥ½
    0.25
    hy
    0.24
    éĻ¤
    0.24
     sä
    0.24
    avar
    0.24
    ecz
    0.24
    ci
    0.23
    cale
    0.23
    Activations Density 1.029%

    No Known Activations