© 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. 2316
    Prev
    Next
    INDEX
    Explanations

    say "consult"

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

    No Comments

    Negative Logits
     morph
    -21.75
     Morph
    -20.50
    morph
    -19.50
    _ev
    -18.25
     mat
    -15.88
     Mor
    -15.81
     Sam
    -15.69
    	ev
    -15.31
     sim
    -15.19
    asser
    -15.13
    POSITIVE LOGITS
     CONS
    46.25
    cons
    45.50
    consult
    44.50
    Consult
    44.00
    Cons
    44.00
     consult
    43.50
     Cons
    43.00
    CONS
    43.00
     consul
    43.00
    .cons
    42.25
    Activations Density 0.064%

    No Known Activations