© 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. 35041
    Prev
    Next
    INDEX
    Explanations

    inducted into

    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
    onaut
    -0.09
    ippers
    -0.09
    lös
    -0.08
     economy
    -0.08
     Ñģобой
    -0.08
    è´§
    -0.08
    å¢Ģ
    -0.08
    á½´
    -0.08
    NULL
    -0.08
    åĮIJ
    -0.08
    POSITIVE LOGITS
    _into
    0.12
    æĻķ
    0.11
     into
    0.11
    Into
    0.10
    lace
    0.10
    èŀįåħ¥
    0.10
    into
    0.10
    represent
    0.09
    åĪ°è¿ĻéĩĮ
    0.09
    åľĪ
    0.09
    Activations Density 0.013%

    No Known Activations