© 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. 63541
    Prev
    Next
    INDEX
    Explanations

    -ative endings and subsequent nouns

    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
    ãģĦãģ¾ãģĻ
    -0.12
    ship
    -0.12
    nt
    -0.12
    lo
    -0.11
    ãģĦãģŁ
    -0.11
    making
    -0.11
    loc
    -0.11
    avigation
    -0.11
    ships
    -0.11
    ãģĦãĤĭ
    -0.10
    POSITIVE LOGITS
    -minded
    0.17
    ity
    0.13
    ITY
    0.12
    ãģĮãĤī
    0.12
    -looking
    0.12
     minded
    0.11
    zza
    0.11
    ye
    0.11
    idad
    0.10
    gle
    0.10
    Activations Density 0.265%

    No Known Activations