© 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. 29920
    Prev
    Next
    INDEX
    Explanations

    case reports rare variations

    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
    FML
    -0.10
    丢äºĨ
    -0.09
    andin
    -0.09
    å¤Ħå¤Ħ
    -0.09
    åıĹåĪ°å½±åĵį
    -0.09
    æĦŁåıĹåĪ°
    -0.09
    ä¹Łä¸įæĥ³
    -0.09
    çŀij
    -0.09
    æĦıè§ģåıįé¦Ī
    -0.09
    è§ī
    -0.09
    POSITIVE LOGITS
    çĹħä¾ĭ
    0.11
    _cases
    0.09
    ç½ķ
    0.09
    å¾®åĪĽ
    0.09
     Extreme
    0.09
    æŀģ端
    0.08
    åı¯è¡Į
    0.08
    ç½ķè§ģ
    0.08
    表æ¼Ķ
    0.08
    åı¯è¡ĮæĢ§
    0.08
    Activations Density 2.136%

    No Known Activations