© 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. 63330
    Prev
    Next
    INDEX
    Explanations

    verb and grammatical relations

    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
    mere
    -0.10
    æįŁ
    -0.09
    INCT
    -0.09
    æľķ
    -0.09
    计
    -0.09
     Ryder
    -0.09
    çķª
    -0.08
    åĩºç¤º
    -0.08
     PCR
    -0.08
    ç¾İèªī
    -0.08
    POSITIVE LOGITS
    åĬ¨ä½ľ
    0.09
    åijĽ
    0.09
    pike
    0.09
    ãģ£ãģ±
    0.09
     acted
    0.08
    (Action
    0.08
    _action
    0.08
    ory
    0.08
    ç¥ľ
    0.08
     vib
    0.08
    Activations Density 0.050%

    No Known Activations