© 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. 5452
    Prev
    Next
    INDEX
    Explanations

    so too

    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
    fabs
    -0.09
    lings
    -0.09
    innen
    -0.09
    éģįåıĬ
    -0.09
    å¤ķ
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    æīĢ以æĪij
    -0.08
    erves
    -0.08
    è¿Ļ对äºİ
    -0.08
    FIT
    -0.08
    POSITIVE LOGITS
     too
    0.09
    _VE
    0.09
    æIJŃ
    0.09
    åĴ¨
    0.09
    èĪªéģĵ
    0.08
     likewise
    0.08
    _Private
    0.08
     też
    0.08
    å®Ľ
    0.08
    éĢĤ
    0.08
    Activations Density 0.036%

    No Known Activations