© 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. 62614
    Prev
    Next
    INDEX
    Explanations

    preposition followed by place 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
    æŃ£çīĪ
    -0.09
    åĸī
    -0.09
    åĢį
    -0.09
    otte
    -0.09
    avers
    -0.08
    ä¿Ĺ
    -0.08
    æ¸łéģĵ
    -0.08
    inha
    -0.08
    èµ·æĿ¥
    -0.08
    omen
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    -anchor
    0.09
    .ss
    0.08
    æĸ°ä¸ĸ纪
    0.08
    éĵ¶è¡Įåį¡
    0.08
    ãĥıãĥ³
    0.08
    erts
    0.08
    å¾ĹæĦı
    0.08
    ä¸Ģ个éĩįè¦ģ
    0.08
    _msgs
    0.08
    Activations Density 0.184%

    No Known Activations