© 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. 16965
    Prev
    Next
    INDEX
    Explanations

    fil / Fil / filaments

    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
     immedi
    -0.10
    rys
    -0.09
    ität
    -0.09
    /Images
    -0.09
     worry
    -0.09
    aling
    -0.09
     worrying
    -0.09
     unknow
    -0.09
    vier
    -0.09
    chal
    -0.08
    POSITIVE LOGITS
     fil
    0.13
    aments
    0.12
     Fil
    0.12
    mpjes
    0.11
    adelphia
    0.11
    teen
    0.11
    thy
    0.11
    fil
    0.10
    amentos
    0.10
    ippo
    0.10
    Activations Density 0.089%

    No Known Activations