© 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. 11182
    Prev
    Next
    INDEX
    Explanations

    attitudes toward

    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
    mitt
    -0.12
     Mitt
    -0.10
    èĿ¼
    -0.09
    æĪij以为
    -0.09
     Sach
    -0.08
    nier
    -0.08
    çªģåıij
    -0.08
    çĴŁ
    -0.08
    éĵ²
    -0.08
    moz
    -0.08
    POSITIVE LOGITS
     attitudes
    0.10
    å©ļ
    0.09
     toward
    0.09
    æĢģ度
    0.09
    ãĤ®ãĥ£
    0.08
     odom
    0.08
     tentang
    0.08
    about
    0.08
    èle
    0.08
    ocate
    0.08
    Activations Density 0.027%

    No Known Activations