© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 689
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.23
     atroc
    -0.23
     Malays
    -0.23
     requestOptions
    -0.23
    åĺīå¹´åįİ
    -0.23
     gratuitement
    -0.22
    omba
    -0.22
    rosse
    -0.22
     onSelect
    -0.22
    åĬłæ²¹
    -0.22
    POSITIVE LOGITS
     paper
    0.27
     box
    0.25
     Fil
    0.25
    '
    0.25
     b
    0.24
     sheet
    0.24
    çĪ¬
    0.24
    ish
    0.24
    /
    0.23
     effective
    0.23
    Activations Density 0.004%

    No Known Activations