© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1767
    Prev
    Next
    INDEX
    Explanations

    cutting or cut

    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
    ozo
    -0.24
    abb
    -0.24
     sick
    -0.24
     Sick
    -0.23
    sla
    -0.23
    ione
    -0.22
    ék
    -0.22
    quals
    -0.22
    ales
    -0.22
    _ste
    -0.21
    POSITIVE LOGITS
    ç²Ĺ
    0.23
    墨
    0.23
     mary
    0.22
    .mozilla
    0.22
    elyn
    0.22
     caveat
    0.21
    åĽ¾æ¡Ī
    0.21
    å½¢çĬ¶
    0.21
    ixture
    0.20
    Parcel
    0.20
    Activations Density 0.004%

    No Known Activations