© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 97150
    Prev
    Next
    INDEX
    Explanations

    Technical or legal documents

    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
    Negative Logits
    eus
    -0.29
    hed
    -0.29
    缮
    -0.29
    yms
    -0.28
    uation
    -0.28
    ÑĢÑĭв
    -0.28
    riz
    -0.27
    ular
    -0.27
    ead
    -0.27
    efe
    -0.27
    POSITIVE LOGITS
    TypeEnum
    0.25
     présence
    0.25
    éĻ¶
    0.25
    æŃ£åĵģ
    0.24
    æĿ¥ä¸įåıĬ
    0.24
    landers
    0.24
    èĴĤ
    0.23
     streamed
    0.23
     (£
    0.23
    streams
    0.23
    Activations Density 0.006%

    No Known Activations