© 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. 17122
    Prev
    Next
    INDEX
    Explanations

    collapse, disintegration, rupture

    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
    çľ¼ç¥ŀ
    -0.09
    缮åħī
    -0.09
    alc
    -0.09
    rovers
    -0.09
    æıĦ
    -0.08
    åħ¥åĽŃ
    -0.08
    çľ¼åħī
    -0.08
    èĺ§
    -0.08
    ãĤ¢ãĥ«
    -0.08
     Bullet
    -0.08
    POSITIVE LOGITS
    å¡Į
    0.20
    å´©
    0.19
     collapse
    0.19
    å´©æºĥ
    0.19
    åĿį
    0.18
    åĢĴå¡Į
    0.17
    åŀ®
    0.17
    collapse
    0.17
    -collapse
    0.17
    Collapse
    0.16
    Activations Density 0.132%

    No Known Activations