© 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. 31317
    Prev
    Next
    INDEX
    Explanations

    speaking or saying actions

    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
    çķĻç»Ļ
    -0.10
    æĺİæĺİ
    -0.09
    骥
    -0.09
    ම
    -0.08
    次è¦ģ
    -0.08
    说æľį
    -0.08
    çĻĸ
    -0.08
    äºīåıĸ
    -0.08
    åī¥ç¦»
    -0.08
     luck
    -0.08
    POSITIVE LOGITS
    åĽŀåºĶ
    0.16
    åIJĮæĦı
    0.13
    çIJĨ解åĴĮ
    0.13
     responds
    0.13
    积æŀģåĵįåºĶ
    0.12
    åıįé¦Ī
    0.12
    åĵįåºĶ
    0.12
    éĺħè§Ī
    0.12
     respond
    0.12
    äºĪ以
    0.11
    Activations Density 0.128%

    No Known Activations