© 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. 23-TRANSCODER-HP
    7. 24332
    Prev
    Next
    INDEX
    Explanations

    software copyright licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è§Ĵ度æĿ¥çľĭ
    -0.26
    amo
    -0.25
    earn
    -0.25
    ìī¬
    -0.24
    è¯ļ
    -0.24
    UpdatedAt
    -0.23
    ri
    -0.23
    ela
    -0.23
    主ç¼ĸ
    -0.23
    é¢Ĩ
    -0.23
    POSITIVE LOGITS
     ofType
    0.27
     blasph
    0.27
     Ips
    0.26
    .Std
    0.26
     lust
    0.26
     slut
    0.25
     ark
    0.25
     ArgumentException
    0.25
     senses
    0.25
     Slut
    0.24
    Activations Density 0.028%

    No Known Activations