© 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. 141467
    Prev
    Next
    INDEX
    Explanations

    Fund

    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
    以ä¸Ĭ
    -0.29
    inject
    -0.28
    FO
    -0.27
    ä»ĬæĻļ
    -0.25
    igator
    -0.25
    inal
    -0.25
    }],
    -0.25
    åħ¬çĽĬæĢ§
    -0.25
     persistence
    -0.25
    ivan
    -0.24
    POSITIVE LOGITS
    .obtain
    0.30
    acements
    0.30
    illard
    0.28
    kov
    0.27
     multiplier
    0.25
     Mart
    0.25
     feast
    0.25
    odings
    0.25
    PCODE
    0.25
    /dir
    0.24
    Activations Density 21.780%

    No Known Activations