© 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. 38052
    Prev
    Next
    INDEX
    Explanations

    greenbelt, greenpoint, greenspan, greenbytes

    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
    åijķ
    -0.10
     Pit
    -0.09
    oved
    -0.09
    éĹ·
    -0.09
    vak
    -0.09
    onia
    -0.09
    bles
    -0.09
    踣
    -0.08
     Ib
    -0.08
    ahead
    -0.08
    POSITIVE LOGITS
     cháy
    0.09
    ä½Ľæ³ķ
    0.09
    å¿Ĺ强
    0.09
    tea
    0.08
    ases
    0.08
    äºĶæľĪ
    0.08
    дж
    0.08
    åĢº
    0.08
     gode
    0.08
    ÑĤик
    0.08
    Activations Density 0.012%

    No Known Activations