© 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. 20305
    Prev
    Next
    INDEX
    Explanations

    ammo sales

    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¸ħçĪ½
    -0.10
    æ¸ħæĻ°
    -0.09
     Portions
    -0.09
    oven
    -0.09
    åĤ¢
    -0.09
    çłį
    -0.08
    åĩī
    -0.08
     Implementation
    -0.08
    æ°Ķæģ¯
    -0.08
    çĪ½
    -0.08
    POSITIVE LOGITS
    .setParameter
    0.10
    å¤§åľ°
    0.09
     Kick
    0.09
    iros
    0.09
    letcher
    0.09
    ÑıÑĤ
    0.09
    娲
    0.09
    æ±ŀ
    0.09
    èįIJ
    0.08
    /course
    0.08
    Activations Density 0.059%

    No Known Activations