© 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. 91273
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
     Bass
    -0.07
     Kitt
    -0.07
     conc
    -0.07
    angen
    -0.07
    avec
    -0.06
     Pont
    -0.06
    oir
    -0.06
     Manit
    -0.06
     Masc
    -0.06
     delt
    -0.06
    POSITIVE LOGITS
     Alter
    0.11
     exhausted
    0.11
     apt
    0.11
     debut
    0.10
     Assist
    0.10
    anter
    0.10
     inventor
    0.10
    ulo
    0.10
    ÄIJ
    0.10
    FORM
    0.10
    Activations Density 0.032%

    No Known Activations