© 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. 19465
    Prev
    Next
    INDEX
    Explanations

    downright or positively

    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
     cape
    -0.08
    KÄ°
    -0.08
    zym
    -0.08
    urb
    -0.08
    çĪ»
    -0.08
    /generated
    -0.08
    alis
    -0.08
    ÑĤÑĮ
    -0.08
    _MORE
    -0.08
     lighten
    -0.08
    POSITIVE LOGITS
    ly
    0.12
    yyy
    0.10
    ted
    0.10
    leys
    0.09
    ads
    0.09
    füh
    0.09
    å°±æĺ¯åľ¨
    0.09
    eters
    0.08
    ments
    0.08
    ingly
    0.08
    Activations Density 0.006%

    No Known Activations