© 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. 50974
    Prev
    Next
    INDEX
    Explanations

    starts prefixes like "S-" or "Bibli-"

    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
    _tc
    -0.09
    çĸıéĢļ
    -0.08
    oard
    -0.08
    jeta
    -0.08
    ç¬Ķ
    -0.08
    èµĦ
    -0.08
    ographs
    -0.08
    bsites
    -0.08
     Shanghai
    -0.08
     Fall
    -0.08
    POSITIVE LOGITS
    èĩªç§°
    0.09
    å®ŀäºĭ
    0.09
    éĨ´
    0.09
    á»Ļ
    0.09
    ä¸įåı¯æĪĸ缺
    0.09
    çīĩåĪ»
    0.09
    èįĶ
    0.09
    _LVL
    0.09
    æī¿åĬŀ
    0.08
    MethodImpl
    0.08
    Activations Density 0.247%

    No Known Activations