© 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. 57086
    Prev
    Next
    INDEX
    Explanations

    power and battery descriptions

    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
    çıŃ
    -0.11
    raq
    -0.08
     Lancaster
    -0.08
    è¡Įãģį
    -0.08
    èı²
    -0.08
    è¡Ķ
    -0.08
    enso
    -0.08
    åıĬ缸åħ³
    -0.08
     DIE
    -0.08
    æĢ»æķ°
    -0.08
    POSITIVE LOGITS
    åij½
    0.10
    кÑĢо
    0.09
    åħħ足
    0.09
    ç¹ĩ
    0.09
    ogg
    0.09
    ogra
    0.08
    è¥Ħ
    0.08
    åºĹéĩĮ
    0.08
    åħħ足çļĦ
    0.08
    財
    0.08
    Activations Density 0.118%

    No Known Activations