© 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. 53745
    Prev
    Next
    INDEX
    Explanations

    Descriptive, broad context

    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
     work
    -0.33
     be
    -0.32
    take
    -0.31
     take
    -0.31
    irst
    -0.30
    be
    -0.30
    .be
    -0.29
    _take
    -0.28
    	be
    -0.27
     Work
    -0.26
    POSITIVE LOGITS
     following
    0.28
     stage
    0.26
     average
    0.26
    Ñħодим
    0.25
    .less
    0.25
     stands
    0.25
    AccessException
    0.25
    imore
    0.25
    UGE
    0.25
     privilege
    0.24
    Activations Density 0.011%

    No Known Activations