© 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. 63031
    Prev
    Next
    INDEX
    Explanations

    Irvine and related place names

    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
    arth
    -0.10
    ½
    -0.09
    èĻ¹æ¡¥
    -0.09
    ess
    -0.08
    身躯
    -0.08
    tor
    -0.08
    rous
    -0.08
    mat
    -0.08
    åĵº
    -0.08
    eline
    -0.08
    POSITIVE LOGITS
    交
    0.08
    icular
    0.08
    izational
    0.08
    keit
    0.08
    umph
    0.08
     foregoing
    0.08
    aal
    0.08
    å°ijä¸įäºĨ
    0.08
    åºĬä¸Ĭ
    0.08
    ä¸Ģä½ĵ
    0.08
    Activations Density 0.011%

    No Known Activations