© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8144
    Prev
    Next
    INDEX
    Explanations

    glass material or compound

    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
    ظ
    -0.10
    edic
    -0.09
    åĭĥåĭĥ
    -0.09
    osh
    -0.09
    asing
    -0.09
    è¿ħ
    -0.09
     ÑĩиÑģл
    -0.08
    stral
    -0.08
    alse
    -0.08
    ashing
    -0.08
    POSITIVE LOGITS
    making
    0.13
    unami
    0.12
    gow
    0.12
    makers
    0.12
    ãģĹãģ¾ãģĨ
    0.12
    maker
    0.12
    room
    0.11
    phalt
    0.11
    boro
    0.11
    عÙĪد
    0.11
    Activations Density 0.015%

    No Known Activations