© 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. 88505
    Prev
    Next
    INDEX
    Explanations

    Introduction/example of a topic

    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
    ilater
    -0.27
    acher
    -0.26
    æĥħ
    -0.26
    PointCloud
    -0.25
    åĨĴ
    -0.24
    PCS
    -0.24
     PCS
    -0.24
     here
    -0.24
    æ¹ľ
    -0.24
     tep
    -0.24
    POSITIVE LOGITS
    xab
    0.29
    å¹³åĿĩæ°´å¹³
    0.26
    igator
    0.26
    retain
    0.26
    说ä¸įåĩº
    0.24
    auses
    0.24
    å°ı游æĪı
    0.24
    arb
    0.24
    reuse
    0.24
     reiterated
    0.24
    Activations Density 0.004%

    No Known Activations