© 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. 5070
    Prev
    Next
    INDEX
    Explanations

    firstName followed by assignment or 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
    spot
    -0.09
    ä¸ĵåįĸ
    -0.09
    ç®Ń
    -0.09
     huyết
    -0.09
    髯
    -0.09
    ¶ļ
    -0.08
    /from
    -0.08
    åĹ£
    -0.08
    åĹī
    -0.08
    çļĦåķĨåĵģ
    -0.08
    POSITIVE LOGITS
    .lastname
    0.12
    akes
    0.10
    orado
    0.09
    ajor
    0.08
    acher
    0.08
    ake
    0.08
    .cs
    0.08
    ialog
    0.08
     dele
    0.08
    ores
    0.07
    Activations Density 0.009%

    No Known Activations