© 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. 49414
    Prev
    Next
    INDEX
    Explanations

    wealth of information or knowledge

    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
    halb
    -0.09
    ç³ĸ
    -0.08
     Lip
    -0.08
    å¯ĨéĽĨ
    -0.08
    éĨĽ
    -0.08
    atum
    -0.08
    èĦĤ
    -0.08
    gment
    -0.08
    å®Įç¾İ
    -0.08
    ials
    -0.07
    POSITIVE LOGITS
    amas
    0.11
    isclosed
    0.10
    ç²¾åĬĽ
    0.10
    ç»ıéªĮåĴĮ
    0.10
    åı£å²¸
    0.10
     knowledge
    0.10
    ocity
    0.09
    å©Ĩ
    0.09
    ä¸įéĢļ
    0.09
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.09
    Activations Density 0.010%

    No Known Activations