© 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. 57620
    Prev
    Next
    INDEX
    Explanations

    habit formation or habitual

    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
    erate
    -0.10
    er
    -0.10
    ernen
    -0.08
    istique
    -0.08
    IMIT
    -0.08
    ermen
    -0.08
     curtain
    -0.08
     spoiler
    -0.08
    DU
    -0.07
     couples
    -0.07
    POSITIVE LOGITS
    cul
    0.11
     Formation
    0.10
     formation
    0.10
    uation
    0.10
    ica
    0.10
    asi
    0.10
    576
    0.10
    rank
    0.09
    ated
    0.09
    Formation
    0.09
    Activations Density 0.003%

    No Known Activations