© 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. 49352
    Prev
    Next
    INDEX
    Explanations

    cherishing and treasuring

    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
    æĭĽåij¼
    -0.10
    çĪ½
    -0.09
    ä¼Ĺ
    -0.09
    _wire
    -0.09
    rig
    -0.08
    éĹ¼
    -0.08
    éŃħåĬĽ
    -0.08
    龸æ°Ķ
    -0.08
    强大
    -0.08
    iates
    -0.08
    POSITIVE LOGITS
    æį§
    0.11
    çıį
    0.10
     possessions
    0.10
    ingly
    0.10
    å®Ŀè´µ
    0.10
    à¸Ļา
    0.10
    è´µ
    0.10
    å®Ŀè´µçļĦ
    0.10
    çıįè´µ
    0.10
    è²´
    0.10
    Activations Density 0.017%

    No Known Activations