© 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. 15283
    Prev
    Next
    INDEX
    Explanations

    suicide and related acts

    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
     liv
    -0.08
    led
    -0.08
     ob
    -0.08
    chie
    -0.07
     nec
    -0.07
    ellow
    -0.07
    endar
    -0.07
     caut
    -0.07
     sweat
    -0.07
     Dil
    -0.07
    POSITIVE LOGITS
    /self
    0.16
     ide
    0.14
     pact
    0.13
     bombings
    0.12
    quia
    0.12
    adge
    0.12
     Isl
    0.11
     bombers
    0.11
    iform
    0.11
     bombing
    0.11
    Activations Density 0.041%

    No Known Activations