© 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. 6644
    Prev
    Next
    INDEX
    Explanations

    dosage forms, devices, inhalation, electronic cigarettes

    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
    _regular
    -0.09
    APA
    -0.08
    ARC
    -0.08
    ä¸įå¿ĺ
    -0.08
    izontal
    -0.08
    åĨ°éĽª
    -0.08
    apa
    -0.08
    å¾Ģ
    -0.08
    _reg
    -0.07
    [](
    -0.07
    POSITIVE LOGITS
    çŃīå¾ħ
    0.11
    èĥ¶åĽĬ
    0.10
    头ä¸Ĭ
    0.10
    æİ£
    0.09
    åĻİ
    0.09
    绽
    0.09
    åĴ³
    0.09
    é«»
    0.09
    åĶµ
    0.09
    .collider
    0.08
    Activations Density 0.334%

    No Known Activations