© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    adjective suffixes (-ous, -ious, -aceous, -uous)

    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
    t
    -0.11
    uated
    -0.10
    's
    -0.10
    swith
    -0.09
    ex
    -0.09
    uates
    -0.09
    ÈĽi
    -0.09
    istic
    -0.09
    strom
    -0.09
    thic
    -0.09
    POSITIVE LOGITS
    ness
    0.33
    NESS
    0.21
    ity
    0.15
    -looking
    0.14
    chwitz
    0.13
    presso
    0.13
    sing
    0.13
    ITY
    0.11
    upport
    0.11
    earch
    0.11
    Activations Density 0.106%

    No Known Activations