© 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. 58154
    Prev
    Next
    INDEX
    Explanations

    spreading war or disease

    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
    _ABI
    -0.10
    ABI
    -0.10
    ìłĪ
    -0.09
    åŃIJåŃĻ
    -0.09
    (sess
    -0.09
    æĺ§
    -0.09
    fk
    -0.09
    åħ»çĶŁ
    -0.08
    èľĥ
    -0.08
    åĭ¤å¥ĭ
    -0.08
    POSITIVE LOGITS
    èĶĵ延
    0.27
    æī©æķ£
    0.18
    çĩİ
    0.17
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    0.16
     spread
    0.16
    æī©å¤§
    0.15
    æī©å±ķ
    0.15
    éģįåıĬ
    0.14
     Spread
    0.14
     spreading
    0.14
    Activations Density 0.152%

    No Known Activations