© 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. 130216
    Prev
    Next
    INDEX
    Explanations

    Normal distribution

    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
    æ¶Ī
    -0.32
    etu
    -0.28
    wn
    -0.26
    产
    -0.26
    aro
    -0.25
     atrás
    -0.25
    uspended
    -0.24
    еÑĤе
    -0.24
    udas
    -0.24
    imd
    -0.24
    POSITIVE LOGITS
    çļĦåĬ¨ä½ľ
    0.28
     toaster
    0.27
     throat
    0.26
     admitting
    0.26
    æݨå¼Ģ
    0.26
    çĵ®
    0.24
     Dean
    0.23
    IRA
    0.23
     Hok
    0.23
     opening
    0.23
    Activations Density 8.379%

    No Known Activations