© 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. 142056
    Prev
    Next
    INDEX
    Explanations

    fail

    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
    ĥĿ
    -0.26
     dialogs
    -0.26
    uke
    -0.26
    ilter
    -0.25
    æijĨåľ¨
    -0.24
     diss
    -0.24
    æĬ½
    -0.24
    -valid
    -0.23
    pest
    -0.23
    arts
    -0.23
    POSITIVE LOGITS
    fulness
    0.29
    ainers
    0.29
    odash
    0.28
    orias
    0.28
    ful
    0.27
    avers
    0.27
    éĨļ
    0.26
    ))^
    0.25
    ë§ī
    0.25
    èıĢ
    0.24
    Activations Density 20.675%

    No Known Activations