© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16924
    Prev
    Next
    INDEX
    Explanations

    personally followed by verbs

    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
    éĻįèIJ½
    -0.09
    èĩªåĬ©
    -0.09
    itel
    -0.09
     EVER
    -0.09
    åĩºåĽ½
    -0.09
    abox
    -0.08
    Associated
    -0.08
    äºīåIJµ
    -0.08
    |RF
    -0.08
    头åıij
    -0.08
    POSITIVE LOGITS
     personally
    0.11
    亲
    0.10
    mente
    0.09
    æģŃ
    0.09
    agan
    0.09
     лиÑĩно
    0.08
    ìłģìľ¼ë¡ľ
    0.08
    ä¸įä¼ļæľī
    0.08
    飧
    0.08
    ະ
    0.08
    Activations Density 0.011%

    No Known Activations