© 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. 49278
    Prev
    Next
    INDEX
    Explanations

    highlight what is strategic or diagnostic

    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
    UNC
    -0.09
    arian
    -0.09
    Jet
    -0.08
    à¸Ŀà¸Ļ
    -0.08
    دت
    -0.08
    éķ¿è¿ľ
    -0.08
    rams
    -0.08
    amin
    -0.08
    Outcome
    -0.08
    çĵ¶
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    çijĹ
    0.10
    亮çĤ¹
    0.10
    çļĦéĩįçĤ¹
    0.10
    çªģåĩºéĹ®é¢ĺ
    0.10
    èĻIJå¾ħ
    0.09
    è¦ģéĹ»
    0.09
    _features
    0.09
    åĭ¤åĬ³
    0.09
    纡
    0.09
    Activations Density 0.026%

    No Known Activations