© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52064
    Prev
    Next
    INDEX
    Explanations

    berry types

    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
    _utilities
    -0.09
    raph
    -0.09
    icz
    -0.08
    Iss
    -0.08
    inx
    -0.08
    nt
    -0.08
    åĬĽéĩı
    -0.08
    é£İåIJ¹
    -0.08
    boro
    -0.08
    otron
    -0.08
    POSITIVE LOGITS
    èĩªçIJĨ
    0.10
    缸åħ³æĸ°éĹ»
    0.10
    é«»
    0.10
    è·£
    0.10
    ãģ¼
    0.09
    ä¸Ģæľµ
    0.09
    磮
    0.08
    CAPE
    0.08
    æľīèī²
    0.08
    èIJ½åľ°
    0.08
    Activations Density 0.001%

    No Known Activations