© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    on

    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
    æ°¸ä¹ħ
    -0.11
    çªĿ
    -0.11
    妥åĸĦ
    -0.10
    HeaderCode
    -0.10
    OffsetTable
    -0.10
    å¤ļä¹ħ
    -0.10
    ä¸Ģæŀļ
    -0.10
    对æīĭ
    -0.09
    æĪ´ä¸Ĭ
    -0.09
    ТÐķ
    -0.09
    POSITIVE LOGITS
    Щ
    0.08
    ä¸Ģä¸ĭåŃIJ
    0.08
    æŃ£è§Ħ
    0.08
     Guardian
    0.07
    bum
    0.07
    éĺĬ
    0.07
    checkout
    0.07
    åĽ´
    0.07
     -
    0.07
     amen
    0.07
    Activations Density 0.105%

    No Known Activations