© 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. 35371
    Prev
    Next
    INDEX
    Explanations

    getting old

    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
    æľīè¿ĩ
    -0.10
    å½ĵ代
    -0.09
    etrics
    -0.09
    èı²
    -0.09
    å¼Ģæ°´
    -0.09
    _py
    -0.09
    odon
    -0.08
    éķ¿å¯¿
    -0.08
    Ñįм
    -0.08
    icable
    -0.08
    POSITIVE LOGITS
    ä¸įéĢĤåIJĪ
    0.11
    çĵ
    0.10
    æ§Ľ
    0.09
    身躯
    0.09
    éĻĦåĬł
    0.09
    çIJ¼
    0.09
    ä¸įéĢĤ
    0.08
    åĿIJ
    0.08
     Relax
    0.08
     McKenzie
    0.08
    Activations Density 0.029%

    No Known Activations