© 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. 96758
    Prev
    Next
    INDEX
    Explanations

    locations

    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£
    -0.97
     dispers
    -0.87
     dispersion
    -0.76
    åĪĨæķ£
    -0.76
     dispersed
    -0.76
    disp
    -0.69
     scatter
    -0.64
     Disp
    -0.62
     disp
    -0.60
     scattering
    -0.59
    POSITIVE LOGITS
    tep
    0.30
     poisoned
    0.30
    æĪ£
    0.28
    è¶³å¤Ł
    0.26
    åIJ¯
    0.26
    æ£ł
    0.25
     gig
    0.25
    .sec
    0.24
    妲
    0.23
    team
    0.23
    Activations Density 0.919%

    No Known Activations