© 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. 26729
    Prev
    Next
    INDEX
    Explanations

    family and relatives

    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
    ling
    -0.10
     Burgess
    -0.10
     imm
    -0.10
    ucha
    -0.10
    bill
    -0.09
     Belle
    -0.09
    ache
    -0.09
    bn
    -0.09
    /chat
    -0.09
     Clubs
    -0.09
    POSITIVE LOGITS
     members
    0.19
    /close
    0.15
     member
    0.15
    -members
    0.13
    members
    0.12
     Members
    0.12
     ties
    0.12
    -member
    0.11
    _member
    0.11
    /community
    0.11
    Activations Density 0.062%

    No Known Activations