© 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. 18529
    Prev
    Next
    INDEX
    Explanations

    celebrity news outlets

    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
    èµŀèµı
    -0.09
    spinner
    -0.09
     disc
    -0.09
    åĩĽ
    -0.09
    好è¯Ħ
    -0.08
     discs
    -0.08
    èĦIJ
    -0.08
    rede
    -0.08
    è¿ĺç®Ĺ
    -0.08
    anner
    -0.08
    POSITIVE LOGITS
    åħ«åį¦
    0.13
    åŁŃ
    0.11
    çķ¸
    0.10
    çĨŁ
    0.09
    mts
    0.09
    æĦıåĽ¾
    0.09
    åĪ«è¯´
    0.09
    çİ«
    0.09
    æѤåĪ»
    0.08
    é©·
    0.08
    Activations Density 0.014%

    No Known Activations