© 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. 30-TRANSCODER-HP
    7. 95827
    Prev
    Next
    INDEX
    Explanations

    say "od" and "ogenous"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dbl
    -0.29
    æĬķåħ¥
    -0.26
    éĢļæĬ¥
    -0.26
    太é«ĺ
    -0.25
    compat
    -0.25
    |int
    -0.25
     Rosenstein
    -0.24
    æݨä»ĭ
    -0.24
    abouts
    -0.24
     folded
    -0.24
    POSITIVE LOGITS
    èle
    0.26
     disap
    0.26
    ä¾ĭè¡Į
    0.26
    åĪĽå»ºå·¥ä½ľ
    0.26
    æŀ¯
    0.26
    .getTransaction
    0.25
    åѤ
    0.25
    stantiate
    0.25
    壮
    0.25
    ApplicationContext
    0.24
    Activations Density 0.884%

    No Known Activations