© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51030
    Prev
    Next
    INDEX
    Explanations

    boundary objects

    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
    ãģ¾ãģ¨
    -0.09
    esen
    -0.09
     ASA
    -0.09
    ç§ģæľį
    -0.08
    ä¸İåħ¶ä»ĸ
    -0.08
    å¨ĥ
    -0.08
    éľ²å¤©
    -0.08
    æĢĽ
    -0.08
     Schwartz
    -0.08
    è¿·
    -0.08
    POSITIVE LOGITS
    çªĦ
    0.10
    è¿Ļä¹Ī说
    0.10
    éĻĦè¿ijçļĦ
    0.10
    çĬ¹
    0.09
    é«ĺéĢŁ
    0.09
    åħħ
    0.09
    .Brand
    0.09
     паÑĢÑĤ
    0.09
    çĭŃçªĦ
    0.09
    éĻĦè¿ij
    0.09
    Activations Density 0.121%

    No Known Activations