© 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. 3151
    Prev
    Next
    INDEX
    Explanations

    gear and equipment

    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
    åľ°æĿ¿
    -0.09
    å¦ĥ
    -0.09
    飨
    -0.09
     chocolates
    -0.09
    辩
    -0.09
    uel
    -0.08
    (KP
    -0.08
    visor
    -0.08
    ÙĪÙĦÙĬ
    -0.08
    InstanceId
    -0.08
    POSITIVE LOGITS
     equipment
    0.21
    è£ħå¤ĩ
    0.20
    åĻ¨æĿIJ
    0.19
    åĻ¨åħ·
    0.19
    设å¤ĩ
    0.18
    Equipment
    0.18
     Equipment
    0.17
    éģĵåħ·
    0.17
    å·¥åħ·
    0.16
    equipment
    0.16
    Activations Density 0.124%

    No Known Activations