© 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. 47045
    Prev
    Next
    INDEX
    Explanations

    fish or fisch followed by related words

    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
    ather
    -0.09
    aths
    -0.08
    atten
    -0.08
     sle
    -0.08
     nihil
    -0.08
    prus
    -0.08
    rens
    -0.08
    ICE
    -0.07
    usat
    -0.07
     indict
    -0.07
    POSITIVE LOGITS
    erman
    0.29
    ermen
    0.22
    ery
    0.19
    pond
    0.18
    amble
    0.18
    eries
    0.18
    mong
    0.17
     aquarium
    0.16
     fry
    0.15
    erm
    0.15
    Activations Density 0.015%

    No Known Activations