© 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. 8491
    Prev
    Next
    INDEX
    Explanations

    far followed by distance/time indicators

    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
    изм
    -0.09
    å¨ĺ
    -0.09
    phant
    -0.08
     Hastings
    -0.08
    ÑĤ
    -0.08
    çĽİ
    -0.08
    ijkstra
    -0.08
    gart
    -0.08
    opher
    -0.08
    uality
    -0.08
    POSITIVE LOGITS
    thest
    0.18
    mland
    0.15
    -reaching
    0.14
     enough
    0.11
     جدا
    0.10
    Enough
    0.10
    adic
    0.10
    OOD
    0.10
    riers
    0.09
    åıĪ好
    0.09
    Activations Density 0.022%

    No Known Activations