© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17351
    Prev
    Next
    INDEX
    Explanations

    promotion and promotional activities

    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
    -0.10
    ness
    -0.09
    _DIP
    -0.09
    ç¾¹
    -0.09
    umen
    -0.09
    æī¹ç¤º
    -0.09
    追踪
    -0.09
    rary
    -0.08
    tracks
    -0.08
    æİĮ声
    -0.08
    POSITIVE LOGITS
    ably
    0.10
    able
    0.09
    禧
    0.09
    PING
    0.09
    ively
    0.08
    enade
    0.08
    ëĭĺ
    0.08
    aggio
    0.08
    /prom
    0.08
    宣æī¬
    0.08
    Activations Density 0.028%

    No Known Activations