© 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. 4015
    Prev
    Next
    INDEX
    Explanations

    abstract nouns ending in -ity

    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
    æĬĬèĩªå·±çļĦ
    -0.10
    rig
    -0.10
    çªŁ
    -0.09
    .glob
    -0.09
    urally
    -0.09
    Ùij
    -0.09
    ·æĸ°
    -0.09
    itably
    -0.09
    thood
    -0.09
    ìłł
    -0.09
    POSITIVE LOGITS
    ful
    0.11
    FUL
    0.10
    /of
    0.08
     kok
    0.08
     Hope
    0.08
    ıklı
    0.08
     sake
    0.08
    庵
    0.08
    legg
    0.08
    cion
    0.08
    Activations Density 0.150%

    No Known Activations