© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53162
    Prev
    Next
    INDEX
    Explanations

    proper names ending in common suffixes

    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
    çĨŁæĤīçļĦ
    -0.12
    ç»ıæµİä½ĵ
    -0.10
    对该
    -0.10
    çĨŁæĤī
    -0.09
    åĪĨ彩
    -0.09
    åľ¨è¿Ļ个
    -0.09
    æĬĬè¿Ļ个
    -0.09
     familiar
    -0.09
    çģ«çĥŃ
    -0.08
    èĪĴéĢĤçļĦ
    -0.08
    POSITIVE LOGITS
    "url
    0.09
    (EXPR
    0.08
    аниз
    0.08
    пиÑģÑĮ
    0.08
    URLException
    0.08
    çon
    0.08
    -Ta
    0.08
    _meter
    0.08
    _Stop
    0.08
    -Smith
    0.08
    Activations Density 0.568%

    No Known Activations