© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5998
    Prev
    Next
    INDEX
    Explanations

    actions tried or completed

    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
    able
    -0.20
    ings
    -0.20
    ÂŃing
    -0.14
    INGS
    -0.13
    ability
    -0.13
    ingly
    -0.13
    eds
    -0.13
    ers
    -0.11
    eing
    -0.11
    ABLE
    -0.11
    POSITIVE LOGITS
    ness
    0.16
    evice
    0.12
    nt
    0.12
     бÑĭ
    0.12
    /cop
    0.12
     ÑĢанее
    0.12
    emo
    0.11
    ÑģÑı
    0.11
    /is
    0.11
    ëĭ¤ëĬĶ
    0.11
    Activations Density 0.978%

    No Known Activations