© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51351
    Prev
    Next
    INDEX
    Explanations

    shatter, smash, fracture

    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
    oris
    -0.10
    é«Ń
    -0.09
    rove
    -0.09
    ä¾ij
    -0.09
    overs
    -0.08
    esty
    -0.08
     massa
    -0.08
    eka
    -0.08
     Matters
    -0.08
    jsx
    -0.08
    POSITIVE LOGITS
    çł´ç¢İ
    0.12
    ä¿¡å¿ĥ
    0.12
    glass
    0.11
    éķľåŃIJ
    0.11
    ties
    0.10
    edException
    0.10
    çİ»çĴĥ
    0.10
     кваÑĢ
    0.10
     glass
    0.10
    uder
    0.09
    Activations Density 0.006%

    No Known Activations