© 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. 33035
    Prev
    Next
    INDEX
    Explanations

    hollywood, hibernate, hating, hiding

    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
     parted
    -0.10
    orna
    -0.09
    enet
    -0.09
     Lal
    -0.09
    ORK
    -0.09
    amera
    -0.08
    ipes
    -0.08
    acob
    -0.08
    ativa
    -0.08
    Ãły
    -0.08
    POSITIVE LOGITS
    ERSHEY
    0.17
    allowed
    0.15
    /h
    0.14
    =h
    0.13
     pyl
    0.13
     handshake
    0.13
     hierarchy
    0.12
    atching
    0.12
     handheld
    0.12
     hinge
    0.12
    Activations Density 0.238%

    No Known Activations