© 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. 9922
    Prev
    Next
    INDEX
    Explanations

    price or currency amounts

    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
    amar
    -0.09
    èĤ¸
    -0.08
    Ltd
    -0.08
    avy
    -0.08
    amm
    -0.07
    uit
    -0.07
     gr
    -0.07
     sü
    -0.07
    æ¶Į
    -0.07
    åħĴ
    -0.07
    POSITIVE LOGITS
    å°ijè§ģ
    0.10
    çĬģ
    0.10
    磶
    0.09
     Ging
    0.09
    åįİå°Ķ
    0.09
    éĴī
    0.09
    éķī
    0.09
    _ctl
    0.09
    è¹ij
    0.09
    åīįæĸ¹
    0.09
    Activations Density 0.036%

    No Known Activations