© 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. 22-TRANSCODER-HP
    7. 130467
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +-+-+-+-
    -0.28
    .$.
    -0.26
    apest
    -0.25
    ãģĦãģĨ
    -0.25
    -packed
    -0.24
    ews
    -0.24
    engl
    -0.24
    ãģ¨ãģĦãģ£ãģ¦
    -0.24
    Creators
    -0.24
    .Dom
    -0.23
    POSITIVE LOGITS
    s
    0.50
    i
    0.46
    er
    0.45
    en
    0.43
    al
    0.42
    an
    0.39
    ed
    0.38
    es
    0.36
    ãĥ³
    0.35
    åľ°
    0.34
    Activations Density 0.355%

    No Known Activations