© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15099
    Prev
    Next
    INDEX
    Explanations

    say "rare characters"

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

    No Comments

    Negative Logits
     pigment
    -15.81
    乳腺
    -14.50
     masking
    -14.50
    ansom
    -14.44
    螺丝
    -14.31
     dolphins
    -14.13
     Dolphin
    -14.13
    胆固醇
    -13.88
     PIX
    -13.56
    ubs
    -13.50
    POSITIVE LOGITS
    颍
    15.13
    Я
    14.63
    elijk
    14.63
    Ż
    14.13
    ória
    14.00
    芗
    13.56
    迓
    13.38
    Ǧ
    13.06
    ky
    13.00
    gew
    13.00
    Activations Density 0.477%

    No Known Activations