© 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. 26972
    Prev
    Next
    INDEX
    Explanations

    twitching, jittering

    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
     Lafayette
    -0.09
    elves
    -0.09
    ries
    -0.09
    Ñĩем
    -0.09
    åģļ强
    -0.09
    ä¸Ģ声
    -0.09
    rys
    -0.09
    æ³ħ
    -0.08
    sword
    -0.08
    æŀ¶
    -0.08
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.10
    å¹ħ度
    0.10
    led
    0.09
    utow
    0.09
    /stretch
    0.09
    gle
    0.08
    kowski
    0.08
    èºħ
    0.08
    onda
    0.08
    è´Łè´£
    0.08
    Activations Density 0.006%

    No Known Activations