© 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. 111903
    Prev
    Next
    INDEX
    Explanations

    sen

    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
    xic
    -0.27
    ous
    -0.27
    ogram
    -0.27
    ationToken
    -0.25
    ä¸Ŀ毫ä¸į
    -0.25
    çīĩ
    -0.25
    ography
    -0.24
    ato
    -0.24
    ously
    -0.24
    ãĥ¼ãĤ¹
    -0.24
    POSITIVE LOGITS
    sense
    0.29
    sampling
    0.28
    logg
    0.28
    hä
    0.27
    æ½ľ
    0.25
    safe
    0.25
    song
    0.25
    sap
    0.25
    IVEN
    0.25
    esk
    0.24
    Activations Density 0.017%

    No Known Activations