© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 963
    Prev
    Next
    INDEX
    Explanations

    admitting or agreeing to actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dispens
    -0.08
     jou
    -0.08
     confiscated
    -0.07
     cre
    -0.07
     ache
    -0.07
    Cam
    -0.07
     reminding
    -0.07
    someone
    -0.07
     Disp
    -0.07
     NEED
    -0.07
    POSITIVE LOGITS
     voluntarily
    0.25
     willingly
    0.23
     volont
    0.18
     willingness
    0.17
     voluntary
    0.16
     capit
    0.14
    /respond
    0.13
     cooperate
    0.13
     accepting
    0.13
     unwilling
    0.13
    Activations Density 1.787%

    No Known Activations