© 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. 9409
    Prev
    Next
    INDEX
    Explanations

    success and its outcomes

    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
    ization
    -0.10
    ize
    -0.10
    /me
    -0.09
    ì¦Ŀ
    -0.09
    å§Ķåī¯ä¹¦è®°
    -0.09
    zelf
    -0.09
    åĩºè·¯
    -0.09
    IZATION
    -0.09
    hip
    -0.09
    çĽĪåĪ©èĥ½åĬĽ
    -0.09
    POSITIVE LOGITS
    ively
    0.13
    fully
    0.11
    iveness
    0.11
    ential
    0.11
    heets
    0.10
    èĢħ
    0.10
    -minded
    0.10
    ä¹ĭéģĵ
    0.09
    èĢħçļĦ
    0.09
    åĴĮåıijå±ķ
    0.09
    Activations Density 0.024%

    No Known Activations