© 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. 32-TRANSCODER-HP
    7. 42717
    Prev
    Next
    INDEX
    Explanations

    code, special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igrant
    -0.28
    æĻ¶ä½ĵ
    -0.26
     pong
    -0.26
    iaÅĤ
    -0.26
    idar
    -0.26
    doll
    -0.26
    ipro
    -0.26
    pong
    -0.25
    _dl
    -0.25
    ió
    -0.25
    POSITIVE LOGITS
     AS
    0.30
    nez
    0.30
    aser
    0.29
    amo
    0.28
    am
    0.28
    åķĦ
    0.28
    em
    0.27
    ets
    0.26
    quete
    0.26
    ax
    0.26
    Activations Density 0.004%

    No Known Activations