© 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. 24-TRANSCODER-HP
    7. 149698
    Prev
    Next
    INDEX
    Explanations

    challenge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imately
    -0.27
     occ
    -0.27
    åıĤçħ§
    -0.26
    urvey
    -0.24
     referencia
    -0.24
    survey
    -0.23
    cling
    -0.23
    imir
    -0.23
    lags
    -0.23
    ulla
    -0.23
    POSITIVE LOGITS
    osos
    0.30
    åĩŃ
    0.27
    æ¿Ģ
    0.27
    ously
    0.27
     fore
    0.26
    rous
    0.24
     lur
    0.24
    åľ¨æ¸¸æĪıä¸Ń
    0.24
    es
    0.24
    (es
    0.24
    Activations Density 1.789%

    No Known Activations