© 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. 52776
    Prev
    Next
    INDEX
    Explanations

    alternative options or kinds

    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
    ening
    -0.10
    ification
    -0.10
    INGS
    -0.09
    /her
    -0.09
    OwnProperty
    -0.09
    åĪĿæģĭ
    -0.09
    rist
    -0.09
    linger
    -0.09
     pháºŃn
    -0.09
    fight
    -0.09
    POSITIVE LOGITS
    åı¯æĥ³
    0.10
    vely
    0.10
    ìłģìĿ¸
    0.10
    å·¥ä½ľä½ľé£İ
    0.09
    è¨ĢãģĪãģ°
    0.09
    éĥ
    0.09
    çĩĥæĸĻ
    0.09
    /New
    0.09
    请çĤ¹åĩ»
    0.09
    æĻĵå¾Ĺ
    0.09
    Activations Density 0.025%

    No Known Activations