© 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. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42793
    Prev
    Next
    INDEX
    Explanations

    health insurance/medical payments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     claim
    -0.50
     claims
    -0.45
     Claims
    -0.41
    claim
    -0.41
     CLAIM
    -0.40
     Claim
    -0.40
    claims
    -0.38
    _claim
    -0.38
     claiming
    -0.37
    Claim
    -0.35
    POSITIVE LOGITS
    ovolta
    0.29
     cy
    0.28
    odox
    0.27
    Cy
    0.26
    egade
    0.25
    çĶ©
    0.25
    ukan
    0.25
    çĮĹ
    0.25
    ä¸ĭå·´
    0.25
    严åİīæīĵåĩ»
    0.24
    Activations Density 0.002%

    No Known Activations