© 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. 27-TRANSCODER-HP
    7. 57424
    Prev
    Next
    INDEX
    Explanations

    first or last

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŃļ
    -0.26
    好åĿı
    -0.26
     Eighth
    -0.26
    侧
    -0.26
    Digit
    -0.26
    æ»Ĥ
    -0.25
    èķĻ
    -0.25
    è·³è·ĥ
    -0.24
     adult
    -0.24
    è·
    -0.24
    POSITIVE LOGITS
     stages
    0.34
     generations
    0.30
     weeks
    0.30
     portions
    0.29
     versions
    0.29
     instances
    0.29
    ertest
    0.28
     editions
    0.28
     sections
    0.28
     subsection
    0.28
    Activations Density 0.004%

    No Known Activations