© 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. 22160
    Prev
    Next
    INDEX
    Explanations

    adjunct, adjunctive, adjuvant

    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
    å¼ĢæľĹ
    -0.09
    è¢ħ
    -0.08
    awi
    -0.08
    à¤ĺ
    -0.08
    åºķ线
    -0.08
    jni
    -0.08
    åIJ¬è§ģ
    -0.08
    åĬ«
    -0.08
    ners
    -0.08
    atics
    -0.08
    POSITIVE LOGITS
    ively
    0.11
    iliary
    0.10
    usk
    0.10
    ective
    0.10
    zar
    0.09
    oes
    0.09
    ive
    0.09
    imate
    0.09
    umbs
    0.08
    IMATE
    0.08
    Activations Density 0.010%

    No Known Activations