© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    array of

    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
    lier
    -0.21
    涯
    -0.20
    大家åĪĨ享
    -0.19
    ä¸Ģ个éĩįè¦ģ
    -0.18
     lẽ
    -0.18
     behalf
    -0.18
    ities
    -0.17
    ça
    -0.17
    osis
    -0.17
    ä¸Ģ件äºĭ
    -0.17
    POSITIVE LOGITS
    ed
    0.28
    cloth
    0.22
    /vector
    0.20
    çĿĢä»ĸ
    0.20
    angement
    0.20
    eer
    0.20
    enic
    0.20
    iances
    0.20
    .isArray
    0.20
    /column
    0.20
    Activations Density 0.078%

    No Known Activations