© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1818
    Prev
    Next
    INDEX
    Explanations

    more [noun]

    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
     Quint
    -0.24
    pee
    -0.24
    羣æŃ£
    -0.23
    etty
    -0.22
    _Man
    -0.22
    clusion
    -0.21
    éĹ¨æ§Ľ
    -0.21
    åĪĿãĤģãģ¦
    -0.21
    arith
    -0.21
    ourse
    -0.21
    POSITIVE LOGITS
    å·©åĽº
    0.28
     rounds
    0.26
     iterations
    0.26
    -than
    0.25
     awaited
    0.24
     ado
    0.24
     refine
    0.23
     refined
    0.23
     awaits
    0.23
    born
    0.23
    Activations Density 0.067%

    No Known Activations