© 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. 34189
    Prev
    Next
    INDEX
    Explanations

    and also

    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
    åĹŁ
    -0.09
    .eq
    -0.08
    缮çĿ¹
    -0.08
    æĪijéĥ½
    -0.08
    è¦ģæ¯Ķ
    -0.08
    绿èī²çݯä¿Ŀ
    -0.08
    绯
    -0.08
    èĥ¸åīį
    -0.08
    ernel
    -0.08
    ä¹Łå¾Ī
    -0.08
    POSITIVE LOGITS
    ISTER
    0.08
    礼æĭľ
    0.08
    å®ŀè¡Į
    0.08
    åĵ²
    0.08
    Ģ
    0.08
     ê³µëıĻ
    0.08
     zakÅĤad
    0.08
    åľ»
    0.08
    atel
    0.08
    仿
    0.08
    Activations Density 0.699%

    No Known Activations