© 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. 39782
    Prev
    Next
    INDEX
    Explanations

    top of the list

    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
    涵
    -0.10
    çİ®
    -0.09
    rous
    -0.09
    æĻ®éĢļè¯Ŀ
    -0.09
    缴è¾ĸ
    -0.08
    mere
    -0.08
    èĽ®
    -0.08
    åıijæī¬
    -0.08
    моÑĢ
    -0.08
    pec
    -0.08
    POSITIVE LOGITS
    顶å±Ĥ
    0.15
    æ¦ľé¦ĸ
    0.13
    顶端
    0.13
    éłĤ
    0.13
    顶å±Ĥ设计
    0.12
    æİĴè¡Įæ¦ľ
    0.12
    /top
    0.12
    å°ĸ
    0.11
    층
    0.11
    顶å°ĸ
    0.11
    Activations Density 0.065%

    No Known Activations