© 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. 25-TRANSCODER-HP
    7. 107083
    Prev
    Next
    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Minor
    -0.24
    igits
    -0.24
     Minimum
    -0.24
    á»ĩu
    -0.24
    FRING
    -0.24
    apon
    -0.24
     Views
    -0.24
     ÑĨиÑĦÑĢ
    -0.24
     Differences
    -0.24
     Card
    -0.23
    POSITIVE LOGITS
    èĢĻ
    0.35
    orer
    0.27
    é¡¹çĽ®çļĦ
    0.27
    é«ĺåĩº
    0.26
    -dot
    0.26
    æİĴéĻ¤
    0.26
    inese
    0.25
    andbox
    0.25
    Exclusive
    0.25
    pers
    0.24
    Activations Density 0.181%

    No Known Activations