© 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. 63105
    Prev
    Next
    INDEX
    Explanations

    refugees and migration

    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
    most
    -0.11
    ities
    -0.10
    åıªè¦ģæľī
    -0.10
    azu
    -0.10
    ç»İ
    -0.09
    enance
    -0.09
    å¨ĺ
    -0.09
    ians
    -0.09
    èĭ¥æľī
    -0.09
    aset
    -0.09
    POSITIVE LOGITS
    ged
    0.09
    renc
    0.09
    åīįæīĢ
    0.08
    edom
    0.08
    irá
    0.08
    anco
    0.08
    ä¸İåıijå±ķ
    0.08
     اÙĦاÙĪÙĦ
    0.08
    ../../../
    0.08
    chsel
    0.08
    Activations Density 0.007%

    No Known Activations