© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18225
    Prev
    Next
    INDEX
    Explanations

    's nickname or abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASTER
    -0.09
    reau
    -0.08
     Colomb
    -0.08
    Wa
    -0.08
     Jenner
    -0.08
    agger
    -0.08
     purs
    -0.08
     OTHER
    -0.08
    lw
    -0.08
    ngr
    -0.08
    POSITIVE LOGITS
     as
    0.34
    (as
    0.27
    —as
    0.24
    as
    0.22
    	as
    0.21
    -as
    0.17
     As
    0.17
    _as
    0.16
    As
    0.15
     nickname
    0.14
    Activations Density 0.200%

    No Known Activations