© 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. 107657
    Prev
    Next
    INDEX
    Explanations

    stock

    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
    aux
    -0.29
    身åŃIJ
    -0.26
    uj
    -0.26
    öm
    -0.25
    éĴ¢ç®¡
    -0.25
    aign
    -0.25
    ux
    -0.25
    avig
    -0.25
    æīij
    -0.24
    çݰ身
    -0.24
    POSITIVE LOGITS
    chy
    0.29
     commissions
    0.28
    åij¨å²ģ
    0.27
     commissioners
    0.27
    æĢª
    0.26
     specialists
    0.25
     patent
    0.24
    пе
    0.24
    ancode
    0.24
     scraps
    0.24
    Activations Density 0.310%

    No Known Activations