© 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. 2010
    Prev
    Next
    INDEX
    Explanations

    archaic 'you' and 'through'

    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
     Âł Âł Âł Âł
    -0.20
    ally
    -0.20
     themselves
    -0.20
    ÑĮÑĤе
    -0.19
    ãĥ³
    -0.19
    åľ°å¸¦
    -0.19
    «
    -0.19
    åĴĮåıijå±ķ
    -0.18
    /de
    -0.18
    sWith
    -0.18
    POSITIVE LOGITS
    ä¿©
    0.27
    -même
    0.24
    hw
    0.22
    UU
    0.21
    åĢij
    0.21
    zelf
    0.21
    self
    0.20
     stesso
    0.20
    /her
    0.20
    GH
    0.20
    Activations Density 0.017%

    No Known Activations