© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3142
    Prev
    Next
    INDEX
    Explanations

    parsing text or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ted
    -0.22
    sWith
    -0.21
    zelf
    -0.19
     bothering
    -0.19
    iming
    -0.19
    ----------------------------------------------------------------------↵
    -0.19
     foreseeable
    -0.19
    tas
    -0.18
    plash
    -0.18
    puted
    -0.18
    POSITIVE LOGITS
    less
    0.27
    ä¸įæ¸ħ
    0.25
    itecture
    0.24
    itude
    0.24
    onom
    0.23
    onomy
    0.22
    ç»ĵæŀĦ
    0.21
    quet
    0.21
    imony
    0.21
    ErrorException
    0.20
    Activations Density 0.076%

    No Known Activations