© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21964
    Prev
    Next
    INDEX
    Explanations

    expressing personal interests or activities

    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
    éĿŀ常éĢĤåIJĪ
    -0.10
    æĽ´éĢĤåIJĪ
    -0.10
    å´Ĩ
    -0.10
    æĶ¯çº¿
    -0.09
    otech
    -0.09
    imson
    -0.09
    inch
    -0.08
    áĥĸ
    -0.08
    resse
    -0.08
    峡
    -0.08
    POSITIVE LOGITS
    åIJ¬åĪ°
    0.09
    åħħè£ķ
    0.09
    帽
    0.09
    çĮľ
    0.09
     ÅĽwiad
    0.09
    _NEG
    0.09
    被人
    0.08
     Peoples
    0.08
    æķ´æ´ģ
    0.08
    èģ½åĪ°
    0.08
    Activations Density 0.050%

    No Known Activations