© 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. 26529
    Prev
    Next
    INDEX
    Explanations

    ion channels

    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
    åĿ³
    -0.09
    å¸ļ
    -0.08
    åĬ¨æĢģ
    -0.08
    Proto
    -0.08
    reator
    -0.08
    çģµæ°Ķ
    -0.08
    鸷
    -0.08
    immel
    -0.08
    åijĬ
    -0.08
    ries
    -0.08
    POSITIVE LOGITS
     Cumberland
    0.11
    éĢļéģĵ
    0.11
    .Channel
    0.11
     Channel
    0.10
    åħħ
    0.10
    æ¬ł
    0.10
    åħ³éŨ
    0.09
    _fwd
    0.09
    æĪ¿éĹ´
    0.09
    Channel
    0.09
    Activations Density 0.946%

    No Known Activations