© 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. 61851
    Prev
    Next
    INDEX
    Explanations

    proposal, plans, and projects

    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
    æ±Ľ
    -0.10
    ç«¥
    -0.09
    表æī¬
    -0.09
    ERAL
    -0.08
    ict
    -0.08
    ç¼İ
    -0.08
    å½¢
    -0.08
    browse
    -0.08
    iom
    -0.08
    åİŁåŀĭ
    -0.07
    POSITIVE LOGITS
    æĸ¹æ¡Ī
    0.14
    计åĪĴ
    0.14
     proposal
    0.13
     thuyết
    0.13
     plans
    0.13
     proposals
    0.12
    æıIJæ¡Ī
    0.12
    proposal
    0.12
     plan
    0.12
    plans
    0.11
    Activations Density 0.133%

    No Known Activations