© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21700
    Prev
    Next
    INDEX
    Explanations

    look up

    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
    eco
    -0.11
    /lic
    -0.11
    chester
    -0.09
    å¸ĿåĽ½
    -0.09
    -placement
    -0.09
    arti
    -0.09
    licit
    -0.09
    鬥
    -0.08
    .aspx
    -0.08
    jal
    -0.08
    POSITIVE LOGITS
    ple
    0.10
    ä¸Ģçľĭ
    0.10
     ple
    0.09
    磶
    0.09
    èµĦæºIJåħ±äº«
    0.09
    ç³ħ
    0.09
    .lookup
    0.09
    æŁ¥éĺħ
    0.09
    å¾Īæ£Ĵ
    0.09
    èļģ
    0.08
    Activations Density 0.048%

    No Known Activations