© 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. 24489
    Prev
    Next
    INDEX
    Explanations

    academic article snippets

    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
    æĭŃ
    -0.29
     resent
    -0.28
     kidding
    -0.27
    hma
    -0.26
     automation
    -0.25
     whilst
    -0.25
     %+
    -0.24
    :href
    -0.24
    详ç»Ĩ
    -0.23
    æĥ³èµ·æĿ¥
    -0.23
    POSITIVE LOGITS
    cono
    0.30
     margin
    0.28
    æ¶Ī
    0.27
     dis
    0.25
    frames
    0.24
    Servi
    0.24
    éŀ
    0.24
    OfWork
    0.24
    odal
    0.24
    porte
    0.24
    Activations Density 0.003%

    No Known Activations