© 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. 30781
    Prev
    Next
    INDEX
    Explanations

    mixed results

    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
    æı¿
    -0.09
    flare
    -0.09
    apro
    -0.08
    .FloatTensor
    -0.08
    UA
    -0.08
    éĹªçĶµ
    -0.08
    çĶ³
    -0.08
    ä¸įä»ħä»ħ
    -0.08
     Gros
    -0.08
    缸åħ³åĨħ容
    -0.08
    POSITIVE LOGITS
    å·¥ç¨ĭè´¨éĩı
    0.12
    好åĿı
    0.11
    è´¨éĩıåĴĮ
    0.10
     quality
    0.10
    Quality
    0.10
    _quality
    0.10
    pell
    0.10
     weather
    0.10
    quality
    0.10
    èģŀãģį
    0.09
    Activations Density 0.024%

    No Known Activations