© 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. 61475
    Prev
    Next
    INDEX
    Explanations

    sedimentary

    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
    æ¡ī
    -0.11
    个çĻ¾åĪĨ
    -0.10
    åĴĮåľ°åĮº
    -0.10
    履约
    -0.10
    .Creator
    -0.10
    æ½ĩæ´Ĵ
    -0.10
    è¯ł
    -0.09
    akah
    -0.09
    æݾ
    -0.09
     Hạ
    -0.09
    POSITIVE LOGITS
    _ps
    0.08
    æ²ī
    0.08
    ARY
    0.08
    æ°¡
    0.08
    ary
    0.08
    ogue
    0.08
    eyes
    0.08
    arian
    0.08
    ardi
    0.08
    race
    0.08
    Activations Density 0.023%

    No Known Activations