© 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. 26516
    Prev
    Next
    INDEX
    Explanations

    words ending in p

    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
    ãģıãĤĭ
    -0.16
    rd
    -0.12
    onne
    -0.11
    point
    -0.10
    ep
    -0.10
    helm
    -0.10
    liness
    -0.10
    pair
    -0.10
    past
    -0.10
    lf
    -0.10
    POSITIVE LOGITS
    ëĭĪëĭ¤
    0.18
    attern
    0.15
    resents
    0.15
    edia
    0.15
    ocalypse
    0.14
    licate
    0.14
    licity
    0.14
    erture
    0.14
    ilogue
    0.13
    ilon
    0.13
    Activations Density 1.299%

    No Known Activations