© 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. 2234
    Prev
    Next
    INDEX
    Explanations

    pe followed by common suffixes

    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
    ses
    -0.27
    sa
    -0.23
    sf
    -0.23
    ãĤĤãģ®
    -0.21
    space
    -0.21
    sel
    -0.21
    ship
    -0.20
    sp
    -0.19
    sen
    -0.19
    evity
    -0.19
    POSITIVE LOGITS
    stry
    0.22
    -être
    0.20
    ptic
    0.19
    å¨ĺ
    0.19
    anuts
    0.19
    pee
    0.18
    ´
    0.18
     ÑģамÑĭе
    0.18
    ¤
    0.17
    Gram
    0.17
    Activations Density 0.034%

    No Known Activations