© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48331
    Prev
    Next
    INDEX
    Explanations

    developmental stages

    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
    éªģ
    -0.10
    ç¼ļ
    -0.10
    ÑĢеб
    -0.09
    æ¢
    -0.09
    æī¹
    -0.08
    UGE
    -0.08
    æĮĩ导ä¸ĭ
    -0.08
    éĺĬ
    -0.08
     evenings
    -0.08
    èĥ¸æĢĢ
    -0.08
    POSITIVE LOGITS
    éĺ¶æ®µ
    0.20
     stages
    0.19
    åıijå±ķéĺ¶æ®µ
    0.18
     stage
    0.18
    éļİ段
    0.18
    stage
    0.17
     ÑįÑĤап
    0.16
     Stage
    0.15
    -stage
    0.15
    Stage
    0.15
    Activations Density 0.183%

    No Known Activations