© 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. 22247
    Prev
    Next
    INDEX
    Explanations

    robot, robotics, robotically, assisted

    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
    ัà¸Ķ
    -0.09
    åijIJ
    -0.08
    æŀľ
    -0.08
    bow
    -0.08
    ktop
    -0.08
     SAM
    -0.08
    borg
    -0.08
    æĬ¥éħ¬
    -0.08
    寿
    -0.08
    íį¼
    -0.08
    POSITIVE LOGITS
    à°³
    0.09
    çªľ
    0.09
    liers
    0.09
    çŃ¾çº¦
    0.09
     Pap
    0.08
    á»ijc
    0.08
    åĬŀåħ¬
    0.08
    æĮijè¡ħ
    0.08
    sy
    0.08
     Mississippi
    0.08
    Activations Density 0.040%

    No Known Activations