© 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. 21504
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    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
    å°ıç»Ħ
    -0.09
    å¤©çľŁ
    -0.09
    ç»Ħ
    -0.09
    çĪ±æĬ¤
    -0.08
    å°±æĿ¥çľĭçľĭ
    -0.08
    agement
    -0.08
    人æµģ
    -0.08
    립
    -0.08
    _rq
    -0.08
    鼶è·Ŀ离
    -0.08
    POSITIVE LOGITS
    enger
    0.10
    поÑĢ
    0.09
    fuse
    0.08
    _SYM
    0.08
    меÑģ
    0.08
    象
    0.08
    entric
    0.08
    enburg
    0.08
    _starts
    0.08
    ResponseType
    0.08
    Activations Density 0.069%

    No Known Activations