© 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. 50916
    Prev
    Next
    INDEX
    Explanations

    switching to or from

    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
    è¡®
    -0.10
    alty
    -0.10
    quite
    -0.09
    oration
    -0.08
    åįķè¯į
    -0.08
    stoff
    -0.08
    ä¸ĩéĩĮ
    -0.08
    istic
    -0.08
    åŃ¦å®¶
    -0.08
     Combo
    -0.08
    POSITIVE LOGITS
    aroo
    0.17
    ero
    0.16
    ï¸
    0.12
    èĩªå¦Ĥ
    0.11
    åĴĮå®ĮåĸĦ
    0.11
    OrCreate
    0.11
    ery
    0.11
    gear
    0.11
    ï¸ı
    0.10
    imize
    0.10
    Activations Density 0.026%

    No Known Activations