© 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. 10296
    Prev
    Next
    INDEX
    Explanations

    street blocks

    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
    æºĥ
    -0.09
    æ°´åºĵ
    -0.09
    owell
    -0.09
    åĭ°
    -0.09
    çľģæķĻèĤ²åİħ
    -0.09
    çݰ代åĨľä¸ļ
    -0.08
    é¹£
    -0.08
    éĻįä½İæĪIJæľ¬
    -0.08
    WOOD
    -0.08
    çĶ¨æīĭ
    -0.08
    POSITIVE LOGITS
    è¡Ĺ
    0.22
    è¡Ĺéģĵ
    0.18
     street
    0.17
    è¡ĹåĮº
    0.17
     streets
    0.15
    street
    0.15
    å··
    0.15
    è¡Ĺ头
    0.15
    _street
    0.15
    è¡Ĺä¸Ĭ
    0.14
    Activations Density 0.174%

    No Known Activations