© 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. 54382
    Prev
    Next
    INDEX
    Explanations

    Dates and months

    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
     ph
    -0.28
    fusc
    -0.26
    å´Ĵ
    -0.26
     lay
    -0.25
     cons
    -0.25
     inc
    -0.24
     man
    -0.24
     cube
    -0.24
     oct
    -0.24
     kar
    -0.24
    POSITIVE LOGITS
    å¾·
    0.62
    de
    0.61
    De
    0.60
    _de
    0.59
     De
    0.59
    -de
    0.59
     de
    0.56
     де
    0.54
    .de
    0.52
    _De
    0.52
    Activations Density 0.017%

    No Known Activations