© 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. 53409
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     helping
    -0.51
     making
    -0.49
     Making
    -0.44
     reducing
    -0.44
     increasing
    -0.41
     leading
    -0.41
     improving
    -0.41
     enabling
    -0.41
     guiding
    -0.41
    leading
    -0.40
    POSITIVE LOGITS
     thinking
    0.52
     talking
    0.45
     studying
    0.44
     wishing
    0.43
     believing
    0.43
     seeking
    0.42
     wanting
    0.42
     Thinking
    0.40
     noticing
    0.39
     hearing
    0.39
    Activations Density 0.312%

    No Known Activations