© 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. 52639
    Prev
    Next
    INDEX
    Explanations

    reportedly followed by verbs

    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
     пÑĢедÑĥÑģ
    -0.10
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
    人æ°ij群ä¼Ĺ
    -0.09
    pv
    -0.09
    trä
    -0.09
    åħļçļĦé¢Ĩ导
    -0.09
    огÑĢам
    -0.08
    IRMWARE
    -0.08
    pill
    -0.08
    åįģä¸īäºĶ
    -0.08
    POSITIVE LOGITS
    iad
    0.10
    ably
    0.08
    nte
    0.08
    ate
    0.08
    磸
    0.08
     Ange
    0.08
     Bá
    0.08
    人士
    0.08
    spe
    0.08
    rey
    0.08
    Activations Density 0.017%

    No Known Activations