© 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. 5258
    Prev
    Next
    INDEX
    Explanations

    rumor and rumour

    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
    管
    -0.10
    çĭŀ
    -0.09
    pell
    -0.09
    åĶ¤
    -0.09
    _FALL
    -0.09
    æĸĩåĮĸèĬĤ
    -0.08
    åĪĩ
    -0.08
    è·¯
    -0.08
    éĥ½æĥ³
    -0.08
    åIJ¯
    -0.08
    POSITIVE LOGITS
    è°£è¨Ģ
    0.19
     rumors
    0.17
     rumours
    0.16
     rumor
    0.15
    rum
    0.15
     Rum
    0.14
    åĻĤ
    0.13
    è°£
    0.13
    ä¼łéĹ»
    0.13
     gossip
    0.12
    Activations Density 0.203%

    No Known Activations