© 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. 52617
    Prev
    Next
    INDEX
    Explanations

    locations (resort, town, mountain)

    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
    缤
    -0.10
    亲åĪĩ
    -0.09
    è´¢åĬĽ
    -0.09
    æĻļéĹ´
    -0.09
    åľŃ
    -0.09
    æ±ŁåĮĹ
    -0.09
    绶
    -0.09
    åIJ¸çº³
    -0.09
    没æĶ¶
    -0.09
    ologist
    -0.09
    POSITIVE LOGITS
    åħ¨åĬĽä»¥èµ´
    0.11
    å°ıéķĩ
    0.10
    beth
    0.10
     industries
    0.09
    å¤§åĽ½
    0.09
    èĵ
    0.09
    _INSERT
    0.08
     resort
    0.08
    仲
    0.08
    è´²
    0.08
    Activations Density 0.097%

    No Known Activations