© 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. 34415
    Prev
    Next
    INDEX
    Explanations

    cent words and suffixes

    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
    sic
    -0.10
    æĻĹ
    -0.10
    ä»ĸ认为
    -0.10
    oder
    -0.09
    iness
    -0.09
    eneg
    -0.09
    ëĦĪ
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    ../../../
    -0.08
    ست
    -0.08
    POSITIVE LOGITS
    rale
    0.11
    uries
    0.11
    imeter
    0.10
    orage
    0.10
    ertainment
    0.10
    ária
    0.09
    大楼
    0.09
    ials
    0.09
    rix
    0.09
    ivot
    0.09
    Activations Density 0.025%

    No Known Activations