© 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. 19-TRANSCODER-HP
    7. 8206
    Prev
    Next
    INDEX
    Explanations

    Conquer/quest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìĶĢ
    -0.24
    çĸijéĹ®
    -0.24
    ãģĵãģĿ
    -0.23
    é¢Ĥ
    -0.23
    comings
    -0.23
    æĹıèĩªæ²»å·ŀ
    -0.23
    toDouble
    -0.22
     colspan
    -0.22
    (Locale
    -0.21
    discussion
    -0.21
    POSITIVE LOGITS
    æĭ¥
    0.26
     обÑĬÑı
    0.24
    /import
    0.23
    nable
    0.22
     ATL
    0.22
     flavorful
    0.22
    ducer
    0.22
    toa
    0.21
    åĴ§
    0.21
    é»ijæļĹ
    0.21
    Activations Density 1.053%

    No Known Activations