© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36739
    Prev
    Next
    INDEX
    Explanations

    details of

    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
    ın
    -0.10
    edback
    -0.09
    ç²¹
    -0.09
    arkin
    -0.09
    éĻĽ
    -0.09
    çĦ¶æĺ¯
    -0.09
    arning
    -0.08
    epar
    -0.08
    大è¡Ĺ
    -0.08
    OfSize
    -0.08
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.10
     details
    0.10
     Details
    0.10
    çķĢ
    0.09
     particulars
    0.09
    ilater
    0.09
    壳
    0.09
    ents
    0.09
    екÑĤоÑĢ
    0.09
    çĹħæĥħ
    0.09
    Activations Density 0.024%

    No Known Activations