© 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. 53370
    Prev
    Next
    INDEX
    Explanations

    vintage and retro items

    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
    çħ¦
    -0.09
    odem
    -0.09
    说çļĦè¯Ŀ
    -0.09
    çļ¿
    -0.09
    /channel
    -0.08
    åĪį
    -0.08
    веÑĤ
    -0.08
    ä»Ĺ
    -0.08
    å©Ģ
    -0.08
    身å¤Ħ
    -0.08
    POSITIVE LOGITS
    elah
    0.09
    -ish
    0.09
    -inspired
    0.09
    iker
    0.09
     Orc
    0.09
    çĶ°
    0.08
    èıı
    0.08
     Hunters
    0.08
    atal
    0.08
    elon
    0.08
    Activations Density 0.016%

    No Known Activations