© 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. 38086
    Prev
    Next
    INDEX
    Explanations

    yogurt and financial products

    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
    çĸł
    -0.11
    æĹłäºº
    -0.09
    éĵĥ
    -0.09
    好äºĨ
    -0.09
    hra
    -0.09
    çĻĸ
    -0.08
    好转
    -0.08
     Bris
    -0.08
     SAT
    -0.08
    çIJĨçĶ±
    -0.08
    POSITIVE LOGITS
    è½Ń
    0.10
    åħ»èĢģéĩij
    0.10
    è´¨
    0.10
    _defaults
    0.09
    _services
    0.09
    velt
    0.09
    æ·±åĮĸ
    0.09
    åį§
    0.09
     Seek
    0.09
    .bank
    0.09
    Activations Density 0.103%

    No Known Activations