© 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. 25474
    Prev
    Next
    INDEX
    Explanations

    nowhere, nobody, nothing

    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
    quelle
    -0.10
    ivec
    -0.10
    ubi
    -0.10
     Amend
    -0.09
    Fred
    -0.09
    dac
    -0.09
    gro
    -0.09
    ück
    -0.09
    arda
    -0.09
    adora
    -0.09
    POSITIVE LOGITS
    ness
    0.12
     else
    0.10
    inz
    0.09
    aters
    0.09
    hawk
    0.09
     seeming
    0.09
    YTE
    0.08
     Gul
    0.08
    -looking
    0.08
    lev
    0.08
    Activations Density 0.010%

    No Known Activations