© 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. 35238
    Prev
    Next
    INDEX
    Explanations

    dividend

    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
    åıģ
    -0.10
    æķ²
    -0.09
    å¥ij
    -0.09
    å¸Ĥåľºè§Ħ模
    -0.09
    æĪĸå¤ļ
    -0.08
    Exclusive
    -0.08
    æĭ¾
    -0.08
    бан
    -0.08
    InBackground
    -0.08
    èĽ°
    -0.08
    POSITIVE LOGITS
    åºľ
    0.10
    MSC
    0.09
    åĮħ袱
    0.09
    åŃ
    0.09
    åŃ½
    0.08
    åĪĨ红
    0.08
    稳å®ļ
    0.08
    åĢľ
    0.08
    彬
    0.08
     dividend
    0.08
    Activations Density 0.041%

    No Known Activations