© 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. 21773
    Prev
    Next
    INDEX
    Explanations

    sports betting, software, platform, shoes

    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
    çĶŁåij½çļĦ
    -0.10
    _SDK
    -0.10
    DCALL
    -0.10
    edException
    -0.09
    osit
    -0.09
     Jets
    -0.09
    iker
    -0.09
    ossal
    -0.09
    èIJ½åħ¥
    -0.09
    泯
    -0.09
    POSITIVE LOGITS
    躬
    0.10
    å¿Ļ
    0.09
     McM
    0.09
    3
    0.09
    秩
    0.08
    å°±å¤Ł
    0.08
    0
    0.08
     Studio
    0.08
    1
    0.08
    umm
    0.08
    Activations Density 0.072%

    No Known Activations