© 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. 49865
    Prev
    Next
    INDEX
    Explanations

    abstract or specific terms

    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£ł
    -0.10
    åľ¨æł¡
    -0.10
    èĿ®
    -0.09
    кÑĢаÑģ
    -0.09
    åĸĦäºİ
    -0.09
    æŁļ
    -0.09
    çĮ®
    -0.09
    åľ¨èģĮ
    -0.08
     lap
    -0.08
    CHANNEL
    -0.08
    POSITIVE LOGITS
    ather
    0.09
     fou
    0.08
    å±ħ
    0.08
     bald
    0.08
    enheim
    0.08
    å°ı康
    0.08
    ivic
    0.08
    iete
    0.08
    å®ļä½į
    0.08
    ä¸ĸ家
    0.08
    Activations Density 0.011%

    No Known Activations