© 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. 2817
    Prev
    Next
    INDEX
    Explanations

    say "evil"

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

    No Comments

    Negative Logits
    质
    -19.13
    qual
    -19.00
    ammen
    -18.38
    注册
    -18.38
    質
    -18.00
     Pres
    -17.25
    Pres
    -16.88
    定量
    -16.88
     qual
    -16.63
     params
    -16.50
    POSITIVE LOGITS
    _ev
    34.25
    Ev
    33.50
     evil
    32.00
    (ev
    32.00
     Evil
    31.38
    _EV
    30.88
     EV
    30.75
    	ev
    29.63
    EV
    29.50
     ev
    29.25
    Activations Density 0.079%

    No Known Activations