© 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. 50704
    Prev
    Next
    INDEX
    Explanations

    cystic

    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
    atham
    -0.11
    è¯ķéªĮåĮº
    -0.10
     اÙĦآخر
    -0.10
    æ¤ħ
    -0.09
    venture
    -0.08
    »
    -0.08
    cation
    -0.08
    inton
    -0.08
    asher
    -0.08
    åįĬå²Ľ
    -0.08
    POSITIVE LOGITS
    ties
    0.12
    ×ķת
    0.12
    inct
    0.10
    ä¸Ģ次次
    0.09
    ingly
    0.09
    mates
    0.09
    ory
    0.09
    ะ
    0.09
    -of
    0.09
    ase
    0.08
    Activations Density 0.041%

    No Known Activations