© 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. 116591
    Prev
    Next
    INDEX
    Explanations

    face to face 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
    uer
    -0.10
     ::=
    -0.09
    ndo
    -0.09
    _bc
    -0.09
     broadly
    -0.08
    rious
    -0.08
    fulness
    -0.08
    bew
    -0.08
    renderer
    -0.08
    tt
    -0.08
    POSITIVE LOGITS
     authentic
    0.10
     with
    0.09
    /exec
    0.09
     Hos
    0.09
     in
    0.09
    ë¡ľ
    0.09
    ãģį
    0.09
    inan
    0.09
     into
    0.09
    /core
    0.09
    Activations Density 0.043%

    No Known Activations