© 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. 17155
    Prev
    Next
    INDEX
    Explanations

    architecture and design decisions

    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
    è°ħ
    -0.09
    çĶ¬
    -0.09
    æģŃåĸľ
    -0.09
    羣å®ŀæĢ§
    -0.08
    oodle
    -0.08
    线索
    -0.08
    æį
    -0.08
    legalArgumentException
    -0.08
    åįĬ导
    -0.08
    bron
    -0.08
    POSITIVE LOGITS
    设计æĸ¹æ¡Ī
    0.12
    æĸ¹æ¡Ī
    0.10
    æķ²
    0.10
    _design
    0.10
     design
    0.09
    设计
    0.09
    ç»ĵæŀĦ
    0.09
     Architecture
    0.09
    解åĨ³æĸ¹æ¡Ī
    0.09
     Aviv
    0.09
    Activations Density 0.230%

    No Known Activations