© 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. 8800
    Prev
    Next
    INDEX
    Explanations

    emotional sentiment

    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
    .gb
    -0.08
     Sharp
    -0.08
    gb
    -0.08
    çļĦçĥŃæĥħ
    -0.08
     chant
    -0.08
     GB
    -0.08
    fts
    -0.08
    çĭĤ欢
    -0.08
     sharp
    -0.08
    .mag
    -0.07
    POSITIVE LOGITS
    æĦŁäºº
    0.13
    ç´łé£Ł
    0.10
    osos
    0.10
    BuilderFactory
    0.09
    åĬ¨äºº
    0.09
    亲æĥħ
    0.09
    ä¹ĭæĥħ
    0.09
    çIJ´
    0.09
    åŁºéĩij管çIJĨ
    0.09
    寡
    0.09
    Activations Density 0.012%

    No Known Activations