© 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. 50961
    Prev
    Next
    INDEX
    Explanations

    per cent

    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
    ðŁı»
    -0.11
    razil
    -0.09
    ÙĨا
    -0.09
    anter
    -0.09
    ues
    -0.08
    湫
    -0.08
    ism
    -0.08
    rieb
    -0.08
    cheng
    -0.08
    anes
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.15
    çݩ家
    0.10
    imate
    0.09
    airo
    0.09
    rey
    0.09
    ÑĭÑĪ
    0.09
    itial
    0.08
    inel
    0.08
    еÑĢж
    0.08
     gÅĤów
    0.08
    Activations Density 0.005%

    No Known Activations