© 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. 53375
    Prev
    Next
    INDEX
    Explanations

    accuracy and validity

    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
    ä¸īæĿ¡
    -0.11
    åīįè¿Ľ
    -0.09
    两æĿ¡
    -0.09
    æ²īéĩį
    -0.09
    æĿŁ
    -0.08
    åįģæĿ¡
    -0.08
    å»ºåĽ½
    -0.08
    ละ
    -0.08
    å®ļå±ħ
    -0.08
    å±¥
    -0.08
    POSITIVE LOGITS
    åı¯éĿł
    0.13
     reliability
    0.12
    åı¯ä¿¡
    0.12
    åı¯éĿłçļĦ
    0.11
     reliable
    0.10
    åı¯éĿłæĢ§
    0.10
     unreliable
    0.10
     Forbes
    0.09
    ril
    0.09
    äºĴèģĶ
    0.09
    Activations Density 0.160%

    No Known Activations