© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21259
    Prev
    Next
    INDEX
    Explanations

    pol or polynomials

    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
    OrUpdate
    -0.10
    lichkeit
    -0.10
    ement
    -0.09
    hips
    -0.09
    iveness
    -0.09
    éģij
    -0.08
    otec
    -0.08
    å¹Ħ
    -0.08
    ÙĪر
    -0.08
    eer
    -0.08
    POSITIVE LOGITS
    ìį¨
    0.12
    vere
    0.11
    ynomials
    0.10
    çĺ¿
    0.10
    ä¸Ģå®ļçļĦ
    0.10
    ת
    0.09
    ovel
    0.09
    اسب
    0.09
    ICY
    0.09
    aised
    0.09
    Activations Density 0.063%

    No Known Activations