© 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. 31746
    Prev
    Next
    INDEX
    Explanations

    banned or blocked from

    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
    åīįä¸ĸ
    -0.09
    åħ¶ä¸Ńæľī
    -0.09
    交æį¢
    -0.09
    ipay
    -0.09
    åĨ
    -0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    è®¤çľŁåŃ¦ä¹ł
    -0.08
    _FREQ
    -0.08
    iner
    -0.08
    çľĭäºĨçľĭ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.13
    ä»»ä½ķ
    0.11
    èĩªæĿ¥
    0.11
    åİķ
    0.10
    æªĢ
    0.10
    ä¸ĭä¸Ģ
    0.10
    isphere
    0.10
    éªĹåıĸ
    0.10
    _contrib
    0.10
    èļģ
    0.09
    Activations Density 0.038%

    No Known Activations