© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90741
    Prev
    Next
    INDEX
    Explanations

    strangling or choking the neck

    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
    nim
    -0.11
    umper
    -0.10
     nib
    -0.10
    uze
    -0.10
     hop
    -0.10
     hopping
    -0.09
    OTP
    -0.09
     troll
    -0.09
     Lind
    -0.09
     Mour
    -0.09
    POSITIVE LOGITS
     throat
    0.35
     choke
    0.34
     choking
    0.33
     neck
    0.31
     choked
    0.31
     thrott
    0.27
     Neck
    0.26
     strang
    0.24
    throat
    0.23
    neck
    0.23
    Activations Density 0.076%

    No Known Activations