© 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. 96664
    Prev
    Next
    INDEX
    Explanations

    ime

    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
     virtually
    -0.25
     pie
    -0.25
     hall
    -0.24
    erties
    -0.24
     full
    -0.24
    nis
    -0.24
     cream
    -0.23
    zes
    -0.23
     assembly
    -0.23
    readcr
    -0.23
    POSITIVE LOGITS
    ä¸ĭä¸Ģ代
    0.30
    wick
    0.29
    缮æłĩ
    0.29
    åĪ¶åº¦æĶ¹éĿ©
    0.28
    çļĦ缮æłĩ
    0.27
    otechn
    0.27
    æĹ©æĻļ
    0.27
     kut
    0.27
    æıŃå¼Ģ
    0.26
    è½½
    0.25
    Activations Density 0.002%

    No Known Activations