© 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. 142129
    Prev
    Next
    INDEX
    Explanations

    Informal writing

    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
     slowly
    -0.27
    eller
    -0.26
    ymous
    -0.26
    æĭ¨
    -0.25
    纨
    -0.24
     dn
    -0.24
    YC
    -0.24
    orts
    -0.24
     awaited
    -0.23
    pill
    -0.23
    POSITIVE LOGITS
    anus
    0.25
     BOTH
    0.24
    æĶ¹éĿ©åıijå±ķ
    0.24
    åIJĪæ³ķæĢ§
    0.24
    @Inject
    0.24
    .provider
    0.23
    ε
    0.23
    acet
    0.23
     contradiction
    0.23
     vad
    0.23
    Activations Density 19.749%

    No Known Activations