© 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. 14-TRANSCODER-HP
    7. 40364
    Prev
    Next
    INDEX
    Explanations

    Random content and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tol
    -0.33
    ër
    -0.27
     Relations
    -0.26
    abra
    -0.25
     Toll
    -0.25
    -Mobile
    -0.24
    éĽĨ
    -0.24
    armor
    -0.24
    andler
    -0.24
    WithTag
    -0.24
    POSITIVE LOGITS
    å¸Ŀçİĭ
    0.26
    book
    0.26
    æĪij们就
    0.25
    å½ĵåľ°æĶ¿åºľ
    0.25
     недо
    0.24
    åĮºåĨħ
    0.24
    swer
    0.24
    æĮĩ示
    0.24
    aries
    0.23
    uts
    0.23
    Activations Density 0.029%

    No Known Activations