© 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. 130420
    Prev
    Next
    INDEX
    Explanations

    astrophysics and space

    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
     march
    -0.27
    olatile
    -0.25
     Donne
    -0.25
    tol
    -0.25
    Unchecked
    -0.25
    _tolerance
    -0.24
    ritable
    -0.23
    æĭĵ宽
    -0.23
    ç¡ķ士
    -0.23
    ding
    -0.23
    POSITIVE LOGITS
    ions
    0.28
     punct
    0.27
    emos
    0.27
    æ£ĺ
    0.26
    ORN
    0.26
    ä
    0.26
    éķ¿
    0.25
    oton
    0.25
    @m
    0.25
    FP
    0.24
    Activations Density 0.009%

    No Known Activations