© 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. 19522
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry

    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
     ocup
    -0.09
    Snap
    -0.09
     Snap
    -0.09
     snap
    -0.09
    å½ķ
    -0.09
    éľ²
    -0.08
    _snap
    -0.08
    çĪ±å°Ķ
    -0.08
    æıĦ
    -0.08
    snap
    -0.08
    POSITIVE LOGITS
    éĽģ
    0.10
    涯
    0.09
    ç«¥
    0.09
    åįģåĩłä¸ª
    0.09
    ç¿ħ
    0.09
    é£ŀè¡Į
    0.08
    Shell
    0.08
     Runner
    0.08
    çĽijçĿ£æ£ĢæŁ¥
    0.08
    bons
    0.08
    Activations Density 0.320%

    No Known Activations