© 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. 33-TRANSCODER-HP
    7. 54370
    Prev
    Next
    INDEX
    Explanations

    healthy/ethical food choices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .connection
    -0.25
     деÑıÑĤелÑĮноÑģÑĤÑĮ
    -0.25
    åºĹ主
    -0.25
    Fraction
    -0.24
     Generator
    -0.24
    éĽ¨æ°´
    -0.24
    讽åĪº
    -0.24
     vej
    -0.24
    _slow
    -0.23
    _sock
    -0.23
    POSITIVE LOGITS
     Levin
    0.27
    iban
    0.26
    osas
    0.25
    å¸ĥ
    0.25
    ivor
    0.25
    ibil
    0.24
     Pry
    0.24
    :before
    0.23
    ivery
    0.23
    CRET
    0.23
    Activations Density 0.016%

    No Known Activations