© 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. 20-TRANSCODER-HP
    7. 142081
    Prev
    Next
    INDEX
    Explanations

    youtube

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    天èĬ±
    -0.27
     Paperback
    -0.27
    FunctionFlags
    -0.26
     Marl
    -0.26
    æ°ĶåĢĻ
    -0.26
    abet
    -0.25
    .Canvas
    -0.24
    éĢļè¡Įè¯ģ
    -0.24
     paperback
    -0.24
    纸质
    -0.24
    POSITIVE LOGITS
     videos
    0.48
    è§Ĩé¢ij
    0.47
     video
    0.44
    videos
    0.42
    .video
    0.41
    Video
    0.40
    (video
    0.39
    YouTube
    0.39
    _video
    0.39
    _VIDEO
    0.39
    Activations Density 55.129%

    No Known Activations