© 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. 19935
    Prev
    Next
    INDEX
    Explanations

    that's where / why

    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
    igin
    -0.09
     CM
    -0.09
    åIJĮ缣
    -0.08
     beautiful
    -0.08
    _RS
    -0.08
    å¼ĢéŨ
    -0.08
    auga
    -0.08
     SOS
    -0.08
    riter
    -0.08
    éĿ¢çĻ½ãģĦ
    -0.08
    POSITIVE LOGITS
    è¿ĻæŶ
    0.14
    è¿ĻæŶåĢĻ
    0.13
    è¿Ļ个æŶåĢĻ
    0.11
    ÐľÐĺ
    0.10
    è¾ħ
    0.10
    æĦıè¯ĨåĪ°
    0.10
     Roose
    0.09
    èĮµ
    0.09
    å°±éľĢè¦ģ
    0.09
    éĻįåĪ°
    0.09
    Activations Density 0.032%

    No Known Activations