© 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. 50246
    Prev
    Next
    INDEX
    Explanations

    day of the month

    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
    æĹ¶æ®µ
    -0.09
    æŃ¤äºº
    -0.09
    çĮ©
    -0.09
    èĤ¡æľ¬
    -0.08
     STATES
    -0.08
    odem
    -0.08
    èĩ¾
    -0.08
    éºŁ
    -0.08
    æļ´
    -0.08
    æŶéĹ´æ®µ
    -0.08
    POSITIVE LOGITS
    åĪ°åºķæĺ¯
    0.10
    olv
    0.08
    antics
    0.08
    åħ¬ç§¯
    0.08
    adol
    0.08
     Ñģобой
    0.08
     Viet
    0.08
    å®ł
    0.08
    chw
    0.08
    ÑİÑĤ
    0.08
    Activations Density 0.048%

    No Known Activations