© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1160
    Prev
    Next
    INDEX
    Explanations

    copyright and license information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    gó
    -0.23
    scal
    -0.23
    .mit
    -0.22
    bm
    -0.22
    pmat
    -0.22
    女ç¥ŀ
    -0.22
    mani
    -0.22
    ParameterValue
    -0.22
     scal
    -0.21
     bum
    -0.21
    POSITIVE LOGITS
     Dw
    0.24
    éĢ»
    0.23
    ki
    0.23
     Preconditions
    0.22
    è°Ł
    0.22
    ieces
    0.21
    -force
    0.20
    ughter
    0.20
    igue
    0.19
    apa
    0.19
    Activations Density 0.001%

    No Known Activations