© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    access to

    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
    沫
    -0.09
    å¨ģåĬĽ
    -0.08
    ä»»æĢ§
    -0.08
    å¢ŀéķ¿çİĩ
    -0.08
    çķ¦
    -0.08
    cano
    -0.08
    ä»ĵä½į
    -0.08
     sponsoring
    -0.08
    imen
    -0.08
     Moh
    -0.08
    POSITIVE LOGITS
     access
    0.10
    åīįæīĢ
    0.10
    ibly
    0.09
    .Access
    0.09
    Ñį
    0.09
    æĢ§å¼º
    0.09
    è¿Ļæīįæĺ¯
    0.09
    åĩĨå¤ĩ好
    0.09
    éĢĶå¾Ħ
    0.09
    å±ł
    0.09
    Activations Density 0.040%

    No Known Activations