© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9199
    Prev
    Next
    INDEX
    Explanations

    bidirectional communication or feedback

    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
    çķĻå®Ī
    -0.09
    å¥Ĺè£ħ
    -0.09
    æ¼Ĩ
    -0.08
    atoria
    -0.08
    éĥ½æĥ³
    -0.08
    åĪ·
    -0.08
     stuck
    -0.08
    ода
    -0.08
    aml
    -0.08
    èĥİ
    -0.08
    POSITIVE LOGITS
    åıįé¦Ī
    0.29
     feedback
    0.25
     Feedback
    0.20
    feedback
    0.19
    Feedback
    0.19
    åĽŀé¦Ī
    0.19
    -feedback
    0.19
    .feedback
    0.18
    åıĮåIJij
    0.18
    _feedback
    0.17
    Activations Density 0.125%

    No Known Activations