© 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. 20273
    Prev
    Next
    INDEX
    Explanations

    political rhetoric

    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
    å§ĵ
    -0.09
    elts
    -0.09
    åĽ¢
    -0.09
    utely
    -0.09
    éĹ®é¢ĺæĺ¯
    -0.09
    驾车
    -0.09
    岬
    -0.09
    éĹŃçݯ
    -0.09
    acct
    -0.08
    è¾Ĺ
    -0.08
    POSITIVE LOGITS
    åı£åı·
    0.14
    æī¿è¯º
    0.13
     rhetoric
    0.13
     заÑıв
    0.11
    .promise
    0.11
    è¨Ģ
    0.10
    èªĵè¨Ģ
    0.10
    声称
    0.10
    空
    0.10
    ä¾Ī
    0.10
    Activations Density 0.065%

    No Known Activations