© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34938
    Prev
    Next
    INDEX
    Explanations

    Elks Lodge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ç»ŀ
    -0.10
    ç¿ĺ
    -0.08
    ief
    -0.08
    åħĶ
    -0.08
     меÑĢопÑĢиÑıÑĤиÑı
    -0.08
    èį·
    -0.08
    oleans
    -0.08
    jure
    -0.08
    çħ§é¡¾
    -0.08
    éĻĦ件
    -0.08
    POSITIVE LOGITS
    .Sdk
    0.10
    pec
    0.10
    ential
    0.10
    ãģĿãģ®ãģ¾ãģ¾
    0.09
     pec
    0.09
    èĻ±
    0.09
    ads
    0.08
    tes
    0.08
    ously
    0.08
    pgsql
    0.08
    Activations Density 0.019%

    No Known Activations