© 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. 9781
    Prev
    Next
    INDEX
    Explanations

    as [adjective/noun] as

    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
    bull
    -0.10
    æľĭåıĭ们对
    -0.10
    åĬĽè¿ĺæĺ¯
    -0.09
    à°³
    -0.09
    yers
    -0.09
    åIJĨ
    -0.09
    并ä¸į代表
    -0.08
    åħ¶æīĢ
    -0.08
    并ä¸įæĦıåij³
    -0.08
    çĶŁäº§çĶŁæ´»
    -0.08
    POSITIVE LOGITS
    letic
    0.10
    _svc
    0.09
    ernaut
    0.08
    laÅŁ
    0.08
    ologically
    0.08
    ographed
    0.08
    被æ·ĺæ±°
    0.08
    able
    0.08
    onic
    0.08
    沿çĿĢ
    0.08
    Activations Density 0.378%

    No Known Activations