© 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. 107359
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     PageSize
    -0.30
    indr
    -0.26
    ioned
    -0.25
     MatSnackBar
    -0.25
    isor
    -0.24
    inality
    -0.24
    (Activity
    -0.24
    owel
    -0.24
    AndView
    -0.24
     pageable
    -0.23
    POSITIVE LOGITS
    cÃŃ
    0.27
     zob
    0.25
    eft
    0.25
    ong
    0.25
    æĪijåıijçİ°
    0.25
    EO
    0.25
     ac
    0.23
    vu
    0.23
     fod
    0.23
    天河
    0.23
    Activations Density 37.560%

    No Known Activations