© 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. 24-TRANSCODER-HP
    7. 150801
    Prev
    Next
    INDEX
    Explanations

    foreign word fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñģкоп
    -0.28
    drag
    -0.28
    strup
    -0.28
    sätze
    -0.27
    ATUS
    -0.26
    Alg
    -0.26
    bur
    -0.24
    ----------č↵
    -0.24
    usat
    -0.24
    ORN
    -0.23
    POSITIVE LOGITS
    Sy
    0.26
    aul
    0.25
    ysz
    0.24
     fran
    0.24
    å®ŀéĻħæĥħåĨµ
    0.24
    çŃĿ
    0.23
     resultant
    0.23
     olmad
    0.23
    è·ĥ
    0.23
    rella
    0.23
    Activations Density 1.035%

    No Known Activations