© 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. 10214
    Prev
    Next
    INDEX
    Explanations

    nodding, nod, nodules

    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
    iling
    -0.09
    yard
    -0.09
    åı©
    -0.09
    unger
    -0.09
    pta
    -0.08
    éĶ¦ç»£
    -0.08
    -oriented
    -0.08
    born
    -0.08
    ropa
    -0.08
    мÑı
    -0.07
    POSITIVE LOGITS
    ðŁı»
    0.13
    ðŁı¼
    0.11
    ellar
    0.11
    æ¶ķ
    0.09
    olean
    0.09
    ding
    0.09
    weg
    0.09
    åĤ¥
    0.09
    ISP
    0.09
    weise
    0.08
    Activations Density 0.005%

    No Known Activations