© 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. 58131
    Prev
    Next
    INDEX
    Explanations

    advice 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
    æĭĤ
    -0.10
    åĨįè§ģ
    -0.09
    åİī害
    -0.09
    arning
    -0.09
    ping
    -0.09
    æĮĩæݧ
    -0.09
    eping
    -0.09
    é¢ĦåijĬ
    -0.09
     chatt
    -0.08
    æĦıèŃĺ
    -0.08
    POSITIVE LOGITS
    å¹ħ
    0.09
    ÑĤол
    0.09
    åĴIJ
    0.08
    ર
    0.08
    _WARNINGS
    0.08
    (Arg
    0.08
    è¿·
    0.08
    licted
    0.08
     маÑģÑĤеÑĢ
    0.08
     targ
    0.08
    Activations Density 0.030%

    No Known Activations