© 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. 58572
    Prev
    Next
    INDEX
    Explanations

    field definitions

    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
    ä¾ĭå¤ĸ
    -0.09
    marvin
    -0.09
    èµŀç¾İ
    -0.09
     Falls
    -0.08
    è§
    -0.08
    åĤ¾
    -0.08
    _uri
    -0.08
    纰
    -0.08
    èĩªçĦ¶èĢĮçĦ¶
    -0.08
     spell
    -0.08
    POSITIVE LOGITS
    aison
    0.11
    åı¯ä»¥çĽ´æİ¥
    0.10
    uhl
    0.09
    宫
    0.09
    äºĶè¡Į
    0.09
    çĸĶ
    0.09
    åĨ·éĵ¾çī©æµģ
    0.08
    aseline
    0.08
    alist
    0.08
    çĶ²
    0.08
    Activations Density 0.023%

    No Known Activations