© 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. 53753
    Prev
    Next
    INDEX
    Explanations

    code/lyrics/website 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
    fid
    -0.28
     di
    -0.27
    noc
    -0.26
    迦
    -0.26
     aqu
    -0.26
    çīĽ
    -0.26
     mos
    -0.26
    {k
    -0.25
    sq
    -0.25
     kap
    -0.25
    POSITIVE LOGITS
    ikers
    0.28
     Uph
    0.27
    ies
    0.26
    åĥı个
    0.25
    èĻļ
    0.24
    hol
    0.24
    PR
    0.24
    åłij
    0.24
     TableCell
    0.24
    绿åĮĸ
    0.23
    Activations Density 0.013%

    No Known Activations