© 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. 107422
    Prev
    Next
    INDEX
    Explanations

    off

    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
    tle
    -0.28
    Generated
    -0.27
     final
    -0.27
    cene
    -0.27
     pur
    -0.25
    té
    -0.25
    ifikasi
    -0.25
    ness
    -0.25
     ramp
    -0.25
    éĥģ
    -0.25
    POSITIVE LOGITS
    ä¸Ģå¼Ģå§ĭå°±
    0.29
     marshaller
    0.28
    éī´
    0.28
    scratch
    0.27
    çĦĬæİ¥
    0.25
     Src
    0.24
     spoof
    0.24
     scratch
    0.24
     scraped
    0.24
    ä¸Ģ次
    0.24
    Activations Density 0.912%

    No Known Activations