© 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. 4211
    Prev
    Next
    INDEX
    Explanations

    you need

    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
     tribute
    -0.09
    ardy
    -0.09
    ional
    -0.09
    charg
    -0.09
    omm
    -0.09
    tribute
    -0.09
    éħį
    -0.09
    è§Ĥçľĭ
    -0.09
    çIJ¦
    -0.08
    åĹ²
    -0.08
    POSITIVE LOGITS
    ActionCode
    0.11
    é¦Ĩ
    0.09
    å½±
    0.09
    æ·ĺ
    0.09
    .motion
    0.08
     ì±ħ
    0.08
    åĽ¾ä¹¦
    0.08
    ÙĩاÙħ
    0.08
    é½
    0.08
    æĭį
    0.08
    Activations Density 0.017%

    No Known Activations