© 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. 4604
    Prev
    Next
    INDEX
    Explanations

    winners are chosen, announced, ranked, receive

    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
    æĥ°
    -0.10
    itis
    -0.09
    ij
    -0.09
    ord
    -0.09
    æĸĹ
    -0.08
    缸åħ³è§Ħå®ļ
    -0.08
    夹
    -0.08
    å°ıãģķ
    -0.08
    èĭ¹
    -0.08
    为æĬĵ
    -0.08
    POSITIVE LOGITS
    庶
    0.09
    éħįåIJĪ
    0.09
    -www
    0.09
    dent
    0.09
    æłª
    0.09
     дол
    0.09
    æĺİ天
    0.09
    ç©°
    0.09
    åĩºæĿ¥
    0.08
    移åĪ°
    0.08
    Activations Density 0.021%

    No Known Activations