© 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. 2796
    Prev
    Next
    INDEX
    Explanations

    Pitt or Heath locations

    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
    er
    -0.25
    ãģĦãģĨ
    -0.21
     Theta
    -0.20
    atter
    -0.20
    rlen
    -0.17
    uster
    -0.17
    erÃł
    -0.17
    minent
    -0.17
    xec
    -0.17
    {:
    -0.17
    POSITIVE LOGITS
    ern
    0.26
    ings
    0.24
    ors
    0.24
    eline
    0.24
    æĻ°
    0.23
    ical
    0.23
    iness
    0.22
    ies
    0.20
    elijk
    0.20
    uring
    0.20
    Activations Density 0.038%

    No Known Activations