© 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. 49508
    Prev
    Next
    INDEX
    Explanations

    make available

    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
    lard
    -0.11
    èĥľä»»
    -0.10
    isty
    -0.09
    оде
    -0.09
    éĵ¢
    -0.09
     Dex
    -0.09
    OTES
    -0.09
    ç²Ł
    -0.09
    é¢ĦæľŁ
    -0.08
    夹
    -0.08
    POSITIVE LOGITS
     availability
    0.18
     available
    0.17
    available
    0.17
    åı¯çĶ¨
    0.16
     Availability
    0.16
     unavailable
    0.15
    Available
    0.15
     Available
    0.15
    availability
    0.14
    Availability
    0.14
    Activations Density 0.061%

    No Known Activations