© 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. 10122
    Prev
    Next
    INDEX
    Explanations

    touch device

    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
    ark
    -0.09
    çĮĽ
    -0.09
    ĶĦ
    -0.08
    maktadır
    -0.08
    æĥ³åİ»
    -0.08
    èĺijèıĩ
    -0.08
    ember
    -0.08
    arity
    -0.08
    å²Į
    -0.08
    ities
    -0.08
    POSITIVE LOGITS
    able
    0.13
    ABLE
    0.12
    outs
    0.11
    stone
    0.10
    ables
    0.10
    å±ı
    0.10
    ableObject
    0.10
    ynet
    0.09
    ableOpacity
    0.09
    缸åĬ©
    0.09
    Activations Density 0.011%

    No Known Activations