© 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. 25-TRANSCODER-HP
    7. 108907
    Prev
    Next
    INDEX
    Explanations

    say the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     footh
    -0.30
    acula
    -0.27
    讨论
    -0.26
    Discussion
    -0.26
    nal
    -0.25
    nav
    -0.25
     plung
    -0.24
    kat
    -0.24
    éĩĮçļĦ
    -0.24
    fulness
    -0.23
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.28
    elry
    0.26
    }px
    0.26
    两ç§į
    0.26
    ä¸Ģ个æĸ°çļĦ
    0.25
    PRICE
    0.25
    ]*(
    0.24
     priced
    0.24
    æĬ¥ä¸ļ
    0.24
    å¦Ĥæŀľä½łæĥ³
    0.24
    Activations Density 0.095%

    No Known Activations