© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3375
    Prev
    Next
    INDEX
    Explanations

    existence of

    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
    ighth
    -0.08
    IGHT
    -0.08
    uset
    -0.08
    asar
    -0.08
    ighted
    -0.08
    elay
    -0.07
    ÑĤом
    -0.07
    conte
    -0.07
    ardin
    -0.07
    evento
    -0.07
    POSITIVE LOGITS
    ent
    0.12
    иÑĤелÑĮ
    0.12
    entially
    0.12
    çĿ
    0.12
    (ed
    0.10
    ential
    0.10
    ÑĥеÑĤ
    0.10
    ently
    0.10
    entials
    0.10
    horn
    0.10
    Activations Density 0.069%

    No Known Activations