© 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. 27023
    Prev
    Next
    INDEX
    Explanations

    apartment buildings and urban areas

    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
    æѧ
    -0.10
    åł°
    -0.10
    nar
    -0.09
    éĤĽ
    -0.09
    .PNG
    -0.09
    ump
    -0.09
    ä¸ŃåĽ½æ±½è½¦
    -0.09
    æ´®
    -0.09
    åĩºåĽ½
    -0.08
    ç»ıè´¸
    -0.08
    POSITIVE LOGITS
    éĺ³åı°
    0.15
    éĥ½å¸Ĥ
    0.14
    ãĥŀãĥ³ãĤ·ãĥ§ãĥ³
    0.13
    Urban
    0.12
    à¸Ħà¸Ńà¸Ļà¹Ĥà¸Ķ
    0.12
     urban
    0.12
    é«ĺ楼
    0.12
     apartment
    0.12
    urban
    0.11
    åľ¨ä¸Ĭæµ·
    0.11
    Activations Density 0.100%

    No Known Activations