© 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. 129370
    Prev
    Next
    INDEX
    Explanations

    and

    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
    which
    -0.39
     which
    -0.38
     whose
    -0.31
     consisting
    -0.31
     których
    -0.31
     containing
    -0.30
     performed
    -0.29
     коÑĤоÑĢÑĭй
    -0.29
    .which
    -0.28
     koje
    -0.28
    POSITIVE LOGITS
     Its
    0.27
    iard
    0.25
    ilar
    0.25
    ãĥģãĥ³
    0.25
    tin
    0.25
    URI
    0.24
     attendant
    0.24
     tentative
    0.23
    Path
    0.23
     explicit
    0.23
    Activations Density 0.029%

    No Known Activations