© 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. 35531
    Prev
    Next
    INDEX
    Explanations

    does not

    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
    nip
    -0.10
    æĪijåıĪ
    -0.10
    ruc
    -0.10
    lix
    -0.09
    rels
    -0.09
    hol
    -0.09
    è¿Ļæīį
    -0.09
    ìn
    -0.09
    rimon
    -0.09
    ä¸Ģ群
    -0.09
    POSITIVE LOGITS
    /do
    0.11
     èĭ¥è¦ģ
    0.11
    /is
    0.10
    omorphic
    0.09
    ctors
    0.09
    åħī彩
    0.09
    ä¹ľ
    0.09
    xygen
    0.09
     NOT
    0.09
    为ä¼ģä¸ļ
    0.08
    Activations Density 0.083%

    No Known Activations