© 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. 27254
    Prev
    Next
    INDEX
    Explanations

    categories and headings

    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
    imenti
    -0.10
    åĪĨæł¡
    -0.09
    污泥
    -0.09
    çĻ¾åĪĨä¹ĭ
    -0.08
    etr
    -0.08
    å®°
    -0.08
    /jav
    -0.08
    对åѦçĶŁ
    -0.08
    管å±Ģ
    -0.08
    ä½Ļ家
    -0.08
    POSITIVE LOGITS
    éľ²
    0.09
    invalidate
    0.08
    æIJŃ
    0.08
    ipa
    0.08
    formance
    0.08
    /thread
    0.08
    Spo
    0.08
    æ¹ĥ
    0.08
    utch
    0.08
    ç±»
    0.08
    Activations Density 0.103%

    No Known Activations