© 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. 48539
    Prev
    Next
    INDEX
    Explanations

    well followed by punctuation

    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
    ä»°
    -0.10
    rus
    -0.10
    /animate
    -0.09
     Bannon
    -0.09
    èij«èĬ¦
    -0.09
    rzy
    -0.09
    åı¤èĢģ
    -0.09
    èĬ±å¼Ģ
    -0.08
    mel
    -0.08
     повеÑĢ
    -0.08
    POSITIVE LOGITS
    неÑĤ
    0.09
    ä½ĵçİ°åľ¨
    0.09
    ä¸įæŃ¢
    0.09
    èĥ¸
    0.08
     chÃŃ
    0.08
    èģĶç½ij
    0.08
    è¨ĵ
    0.08
    -net
    0.08
     &_
    0.08
     piv
    0.08
    Activations Density 0.026%

    No Known Activations