© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12432
    Prev
    Next
    INDEX
    Explanations

    public transport and rail

    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
    Negative Logits
    åĶĽ
    -0.11
    鬣
    -0.11
     Rear
    -0.11
    çĤ¹æ»´
    -0.09
    äºĶæĺŁ
    -0.09
    å¹²æ¶ī
    -0.09
    openh
    -0.09
    borg
    -0.09
    é«ĺ涨
    -0.09
    rear
    -0.09
    POSITIVE LOGITS
    éĵģè·¯
    0.15
    轨éģĵ交éĢļ
    0.15
    åľ°éĵģ
    0.15
    çģ«è½¦
    0.14
    交éĢļ
    0.14
     rail
    0.14
     railway
    0.13
    รà¸ĸà¹Ħà¸Ł
    0.12
    é«ĺéĵģ
    0.12
     train
    0.12
    Activations Density 0.110%

    No Known Activations