© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23500
    Prev
    Next
    INDEX
    Explanations

    most followed by intensifiers

    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
    æľĢåıĹ
    -0.10
    iest
    -0.10
    å®ĮåĸĦçļĦ
    -0.10
    åij¼å£°
    -0.10
     McCart
    -0.10
    é¹ħ
    -0.09
    æľĢ容æĺĵ
    -0.09
    opens
    -0.09
    hoot
    -0.09
    íį¼
    -0.09
    POSITIVE LOGITS
    åĽ½å®¶éĺŁ
    0.11
    sWith
    0.10
     Ler
    0.08
    羣çļĦå¾Ī
    0.08
    mdl
    0.08
    æĶĢ
    0.08
    _readable
    0.08
    ÅĽl
    0.08
    éĶħçĤī
    0.08
    ç±
    0.08
    Activations Density 0.041%

    No Known Activations