© 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. 18699
    Prev
    Next
    INDEX
    Explanations

    square root, square wave, square-free

    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
    åħħæ²Ľ
    -0.09
    ë£Į
    -0.09
    enders
    -0.09
    unes
    -0.09
     Louisville
    -0.09
    ents
    -0.09
    åŃ¦å®¶
    -0.09
    osph
    -0.08
    oplast
    -0.08
     plea
    -0.08
    POSITIVE LOGITS
    pants
    0.11
    ish
    0.11
    -minded
    0.11
     footage
    0.10
    mates
    0.10
    wares
    0.10
     minded
    0.10
    pped
    0.10
    holders
    0.10
    ever
    0.10
    Activations Density 0.039%

    No Known Activations