© 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. 56305
    Prev
    Next
    INDEX
    Explanations

    free download print

    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
    quate
    -0.09
     DVDs
    -0.09
    ulum
    -0.08
    èĴ¿
    -0.08
    compareTo
    -0.08
    åѤ
    -0.08
    åıĪ称
    -0.08
    å®ģ
    -0.08
    .records
    -0.08
    ship
    -0.08
    POSITIVE LOGITS
    æīĵåį°
    0.13
    åħįè´¹
    0.11
     free
    0.10
    download
    0.10
    åī¯æľ¬
    0.10
    模æĿ¿
    0.10
    ä¸ĭè½½
    0.10
    .download
    0.09
    èĩªçĶ±
    0.09
    İ·
    0.09
    Activations Density 0.034%

    No Known Activations