© 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. 12-TRANSCODER-HP
    7. 22853
    Prev
    Next
    INDEX
    Explanations

    Place Names/Proper Nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jing
    -0.25
    åĨ°åĨ·
    -0.25
     redhead
    -0.24
    æĶ¿åĬ¡
    -0.24
     regime
    -0.23
     dich
    -0.23
     consciously
    -0.23
    illet
    -0.23
     ultra
    -0.23
    ynom
    -0.23
    POSITIVE LOGITS
    泡
    0.27
    oscope
    0.27
     inc
    0.27
    COPE
    0.25
    ä¼łç»Ł
    0.25
    stalk
    0.25
    æĹĹå¸ľ
    0.24
    ::↵
    0.24
    ä¸Ģè¾ĪåŃIJ
    0.23
    å¸Ľ
    0.23
    Activations Density 0.009%

    No Known Activations