© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55273
    Prev
    Next
    INDEX
    Explanations

    solely followed by preposition or attribution

    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
    oulos
    -0.08
    avour
    -0.08
    soon
    -0.08
    quo
    -0.08
    angan
    -0.08
    blink
    -0.08
    com
    -0.08
    OrNull
    -0.08
    ogue
    -0.08
    OrCreate
    -0.08
    POSITIVE LOGITS
    为äºĨ让
    0.11
    åĩºäºİ
    0.11
    ãģ«ä¹Ĺ
    0.11
    éĴ§
    0.11
    为广大
    0.11
    /reference
    0.10
    isel
    0.10
    icc
    0.09
    çĸıæķ£
    0.09
    éªł
    0.09
    Activations Density 0.003%

    No Known Activations