© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22298
    Prev
    Next
    INDEX
    Explanations

    control and lack of control

    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
     ull
    -0.09
    ä¾Ŀæīĺ
    -0.09
    ullo
    -0.08
    _func
    -0.08
    åħĥ
    -0.08
    _rb
    -0.08
    supported
    -0.08
    oad
    -0.08
    åĬŁèĥ½
    -0.08
    ä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    åı¯æݧ
    0.21
    æݧåĪ¶
    0.13
     control
    0.13
    æĬĬæݧ
    0.12
    å¤ĸéĥ¨
    0.12
     uncont
    0.12
    çļĦåĬªåĬĽ
    0.12
    æİĮæݧ
    0.12
    ä½łèĩªå·±
    0.12
     æݧ
    0.11
    Activations Density 0.061%

    No Known Activations