© 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. 35-TRANSCODER-HP
    7. 40073
    Prev
    Next
    INDEX
    Explanations

    code, abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actories
    -0.27
    åī§
    -0.27
    çļ´
    -0.25
    çļĦåīįæıIJ
    -0.25
     overweight
    -0.25
     bucks
    -0.25
    éģģ
    -0.25
    对åѦçĶŁ
    -0.24
    æĹ¢
    -0.24
    æĮº
    -0.24
    POSITIVE LOGITS
    ime
    0.42
    imes
    0.36
    IME
    0.36
    tor
    0.31
    imei
    0.31
     Im
    0.30
    ivol
    0.30
    Im
    0.30
    inal
    0.29
    emax
    0.29
    Activations Density 0.018%

    No Known Activations