© 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. 61410
    Prev
    Next
    INDEX
    Explanations

    ceiling

    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
    åħ³éŨ
    -0.11
    ä¿Ŀé²ľ
    -0.09
    slash
    -0.09
    icut
    -0.09
    ä»ĭ
    -0.09
    éĹŃ
    -0.08
    åħ¥åĽŃ
    -0.08
    åłµ
    -0.08
    ä¹°åĪ°
    -0.08
    çĻ¸
    -0.08
    POSITIVE LOGITS
    天èĬ±æĿ¿
    0.21
     ceiling
    0.16
    åIJĬ顶
    0.16
     Ceiling
    0.16
     ceilings
    0.15
    天èĬ±
    0.15
    顶
    0.12
     trần
    0.12
    å±ĭ顶
    0.12
     menn
    0.11
    Activations Density 0.070%

    No Known Activations