© 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. 23015
    Prev
    Next
    INDEX
    Explanations

    leave out or leave the

    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
    å¿ĥè¡Ģ
    -0.10
    æİĮ
    -0.10
    颦
    -0.10
    ç®ħ
    -0.09
    éħ¹
    -0.09
     revive
    -0.09
     Tro
    -0.08
    ä»ĸä¹Ł
    -0.08
    åºĬä¸Ĭ
    -0.08
    浦
    -0.08
    POSITIVE LOGITS
    åīĬå¼±
    0.09
    iasco
    0.09
    åīįåįģ
    0.09
    olg
    0.09
    angen
    0.09
    gun
    0.08
    atto
    0.08
    æ£ł
    0.08
    æ¸IJ
    0.08
    åĪł
    0.08
    Activations Density 0.031%

    No Known Activations