© 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. 2894
    Prev
    Next
    INDEX
    Explanations

    quarter or quarter-

    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
    /disable
    -0.23
    ../
    -0.22
    urat
    -0.21
    urations
    -0.20
    ISTER
    -0.20
    éĽĢ
    -0.20
    entifier
    -0.19
     foregoing
    -0.18
    urator
    -0.18
    dish
    -0.18
    POSITIVE LOGITS
    -long
    0.31
    -inch
    0.23
    -mile
    0.23
    aire
    0.23
    plex
    0.23
    naire
    0.23
    glass
    0.21
    -century
    0.21
    /oct
    0.21
    lies
    0.21
    Activations Density 0.013%

    No Known Activations