© 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. 3719
    Prev
    Next
    INDEX
    Explanations

    starts with str followed by specific endings

    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
    enty
    -0.12
    pest
    -0.10
    ë¥ľ
    -0.09
    çĿ¦
    -0.09
    atsu
    -0.09
    ะ
    -0.08
    agonal
    -0.08
    ingroup
    -0.08
     chắn
    -0.08
    ãĥ³ãĤ°
    -0.08
    POSITIVE LOGITS
    aight
    0.13
    ategy
    0.12
    ategic
    0.12
    ively
    0.12
    ategies
    0.11
    ATEGY
    0.10
    pped
    0.10
    ural
    0.10
    اع
    0.10
    .fromCharCode
    0.10
    Activations Density 0.066%

    No Known Activations