© 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. 61891
    Prev
    Next
    INDEX
    Explanations

    Ascending, stairs, ladder

    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
    åĩºæīĭ
    -0.10
    ä¸įåĨįæĺ¯
    -0.10
    èĺ¸
    -0.09
    íĪ¬
    -0.09
    å¼Ģåı£
    -0.09
    æ¼ł
    -0.09
    ëħIJ
    -0.09
    æĿŁ
    -0.08
    ombo
    -0.08
    æī§
    -0.08
    POSITIVE LOGITS
    楼梯
    0.18
    梯
    0.16
     stairs
    0.15
    åı°éĺ¶
    0.15
     ladder
    0.14
     stair
    0.14
    çĶµæ¢¯
    0.14
    æĶĢçĻ»
    0.13
    Ascending
    0.13
     ascent
    0.12
    Activations Density 0.243%

    No Known Activations