© 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. 97680
    Prev
    Next
    INDEX
    Explanations

    Research or technical documents

    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
    æĤ¬
    -0.30
    WR
    -0.27
    án
    -0.26
    溪
    -0.26
     sunk
    -0.26
    _WR
    -0.26
    cribe
    -0.25
     filmy
    -0.25
    å¼
    -0.25
    趣
    -0.25
    POSITIVE LOGITS
    .UTF
    0.26
    asmus
    0.25
    åĨįä¹Ł
    0.25
     vengeance
    0.25
    Ãły
    0.24
    ä¸Ńä¿¡
    0.24
    æŀķ
    0.24
    åŃ©
    0.23
     cn
    0.23
    quent
    0.23
    Activations Density 0.001%

    No Known Activations