© 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. 61938
    Prev
    Next
    INDEX
    Explanations

    years of experience

    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
    езн
    -0.11
    _RG
    -0.10
    çĤ¹å¤ļ
    -0.10
    FileType
    -0.10
    ä¸ī个æľĪ
    -0.09
    åħ«åį¦
    -0.09
    åŃĻåŃIJ
    -0.09
    ACH
    -0.09
    /qu
    -0.09
    VERS
    -0.09
    POSITIVE LOGITS
    äºĮåįģå¹´
    0.09
    -old
    0.09
    èģĮä¸ļ
    0.09
    è¿ĽæŃ¥
    0.09
    é¾Ħ
    0.09
    terra
    0.08
    EventHandler
    0.08
    èģĮä¸ļçĶŁæ¶¯
    0.08
     conditioning
    0.08
    _tokenize
    0.08
    Activations Density 0.077%

    No Known Activations