© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20367
    Prev
    Next
    INDEX
    Explanations

    Days Tanzania Camping Safari

    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
     alma
    -0.09
    ä½ŀ
    -0.09
    çĹŀ
    -0.09
     ê°Ļ
    -0.09
    è§īå¾Ĺ
    -0.09
    ç¿Ĵæħ£
    -0.08
    ç½Ħ
    -0.08
    çĽ¸äº²
    -0.08
    å°±è§īå¾Ĺ
    -0.08
    åĬ¨äºº
    -0.08
    POSITIVE LOGITS
    _EMIT
    0.09
     Cue
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
    utton
    0.08
    æĶ»çķ¥
    0.08
    ä½łä¼ļåıijçİ°
    0.08
    è°ľ
    0.08
     leads
    0.08
    æŃ£å½ĵ
    0.08
    åī§æĥħ
    0.07
    Activations Density 0.059%

    No Known Activations