© 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. 63397
    Prev
    Next
    INDEX
    Explanations

    urban slums and streets

    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
    åħ³åı£
    -0.10
    åīįç½®
    -0.09
    ä¹ĭ乡
    -0.09
    exus
    -0.09
    æ¦ī
    -0.09
    illus
    -0.09
    桦
    -0.08
    åĨĴ
    -0.08
    appa
    -0.08
    æ·¡å®ļ
    -0.08
    POSITIVE LOGITS
    æ£ļ
    0.13
     street
    0.12
    åŀĥåľ¾æ¡¶
    0.11
     urban
    0.10
     urb
    0.10
    ä¸IJ
    0.10
    åŀĥåľ¾
    0.10
    Street
    0.10
     STREET
    0.10
    éĥ½å¸Ĥ
    0.09
    Activations Density 0.095%

    No Known Activations