© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9663
    Prev
    Next
    INDEX
    Explanations

    names followed by possessive 's or last names

    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
    infeld
    -0.09
    æµģè¡ĮçļĦ
    -0.09
    _MUX
    -0.09
    .gs
    -0.09
    ensch
    -0.09
    /ajax
    -0.09
    çĪ¬
    -0.09
    sı
    -0.08
     ejac
    -0.08
    æĩĴ
    -0.08
    POSITIVE LOGITS
     alone
    0.13
    ä¸ºæł¸å¿ĥçļĦ
    0.11
    alone
    0.10
    æĺİæĺŁ
    0.10
    åĩºå¢ĥ
    0.10
     sole
    0.09
    åıĬ缸åħ³
    0.09
    çĭ¬è§Ĵ
    0.09
    个人
    0.09
    çīµå¤´
    0.09
    Activations Density 0.174%

    No Known Activations