© 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. 7615
    Prev
    Next
    INDEX
    Explanations

    wings or winged

    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
    illion
    -0.10
    ble
    -0.10
    vik
    -0.10
    éĽĦåİļ
    -0.10
    ities
    -0.10
    åĪĽæĸ°åŀĭ
    -0.10
    ëĭ¹
    -0.10
    ãģ¦ãĤĤ
    -0.09
    å£ħ
    -0.09
    ince
    -0.09
    POSITIVE LOGITS
    aroo
    0.09
    len
    0.08
    çĦ¶æĺ¯
    0.08
    air
    0.08
    tips
    0.08
    ï¸
    0.08
    olio
    0.08
     fate
    0.08
    zeug
    0.08
    èĥĽ
    0.08
    Activations Density 0.010%

    No Known Activations