© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47503
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

    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
    Negative Logits
    åĵ¥åĵ¥
    -0.09
    eel
    -0.09
    rene
    -0.08
    chine
    -0.08
    ë§ģ
    -0.08
    éģĹå¿ĺ
    -0.08
    NSE
    -0.08
    éĹŃ
    -0.08
    åıįåĵį
    -0.08
    纽
    -0.08
    POSITIVE LOGITS
    MOST
    0.10
    çĶļ
    0.09
    éļ¾åº¦
    0.09
    æĿijæĿijæ°ij
    0.09
    ä¸Ģç»ı
    0.09
    åħ¬å®īå±Ģ
    0.08
    第ä¸Ģå±Ĭ
    0.08
    ä¸ĢæŦ
    0.08
    ç
    0.08
    æĸ°å»º
    0.08
    Activations Density 0.033%

    No Known Activations