© 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. 96782
    Prev
    Next
    INDEX
    Explanations

    0

    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
    æĶ¯ä»ĺ
    -0.39
     paid
    -0.38
     paying
    -0.36
    ä»ĺ
    -0.30
     payment
    -0.29
     Paid
    -0.28
     payer
    -0.28
    å§IJ妹
    -0.28
     Redistribution
    -0.28
     Riy
    -0.27
    POSITIVE LOGITS
    ents
    0.29
     activities
    0.29
    åĩĢ
    0.28
     net
    0.27
    activities
    0.26
     Net
    0.25
    alted
    0.25
    activity
    0.25
     factor
    0.25
     Activities
    0.25
    Activations Density 0.103%

    No Known Activations