© 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. 35540
    Prev
    Next
    INDEX
    Explanations

    simplistic and -istic words

    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
    ings
    -0.10
    ละ
    -0.10
    able
    -0.09
    éĽªå±±
    -0.09
    ables
    -0.08
    çī¹éķ¿
    -0.08
    éªĬ
    -0.08
    ault
    -0.08
    OrCreate
    -0.08
    iaux
    -0.08
    POSITIVE LOGITS
    -minded
    0.15
    -leaning
    0.13
    主ä¹īèĢħ
    0.11
     minded
    0.10
    ism
    0.10
    ities
    0.10
    åĥı个
    0.10
     manner
    0.09
    -looking
    0.09
    主ä¹ī
    0.09
    Activations Density 0.056%

    No Known Activations