© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9328
    Prev
    Next
    INDEX
    Explanations

    teen wolf, fantasy novels, legal terms

    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
    çĸıéĢļ
    -0.14
    دا
    -0.10
    çĬĬ
    -0.10
    篡
    -0.09
    stre
    -0.09
    åľ¨åĮĹ京
    -0.09
    ISO
    -0.08
    olib
    -0.08
    妻
    -0.08
    ippo
    -0.08
    POSITIVE LOGITS
    以æŃ¤
    0.10
    åĨ³å¿ĥ
    0.09
    æ¸ħæ°´
    0.09
    çĤľ
    0.09
    mma
    0.09
    _nv
    0.09
    æĻĶ
    0.09
    osl
    0.08
    æĽľ
    0.08
    çĥ¨
    0.08
    Activations Density 0.005%

    No Known Activations