© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2178
    Prev
    Next
    INDEX
    Explanations

    sampling

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ent
    -18.38
    忘记了
    -17.38
     tubes
    -17.00
     fort
    -16.88
    _fac
    -16.63
    iani
    -16.50
    邮轮
    -16.50
     tube
    -16.50
    传奇
    -16.25
    疮
    -16.25
    POSITIVE LOGITS
    采
    51.75
     sampling
    26.25
     Sampling
    26.00
     sampler
    25.63
    Sampling
    25.13
    sampling
    24.75
    采集
    24.25
     Sampler
    23.88
    採
    23.75
    -rec
    23.50
    Activations Density 0.059%

    No Known Activations