© 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. 50747
    Prev
    Next
    INDEX
    Explanations

    resemblance and similarity

    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
    Scoped
    -0.09
    ivers
    -0.09
    ä¸Ģ度
    -0.08
    ento
    -0.08
    èĮĥçķ´
    -0.08
    éľĵ
    -0.08
    intern
    -0.08
    å¢ĥçķĮ
    -0.08
    èĩªåĪ¶
    -0.08
    çł´
    -0.08
    POSITIVE LOGITS
     resemblance
    0.17
    çĽ¸ä¼¼
    0.16
     similarity
    0.15
     resembl
    0.15
     resemble
    0.14
     resembles
    0.14
     resembled
    0.12
     similarities
    0.12
     likeness
    0.11
    模仿
    0.11
    Activations Density 0.074%

    No Known Activations