© 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. 112137
    Prev
    Next
    INDEX
    Explanations

    best

    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
    <data
    -0.25
     trä
    -0.25
    osos
    -0.24
     absorbing
    -0.24
    建ç«ĭèµ·
    -0.24
    materials
    -0.23
    å®Ŀ
    -0.23
    SUR
    -0.23
    ingerprint
    -0.23
    ä¿Ŀè´¹
    -0.23
    POSITIVE LOGITS
    æķĪ
    0.32
    Òij
    0.31
    ä½³
    0.25
    atten
    0.24
    oria
    0.24
    ERT
    0.24
    æ°´å¹³
    0.24
    临æŶ
    0.24
     cycle
    0.24
    æ·¡
    0.24
    Activations Density 0.003%

    No Known Activations