© 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. 53816
    Prev
    Next
    INDEX
    Explanations

    say "edit" or "editor"

    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
    ç¼ĸè¾ij
    -0.52
     edit
    -0.52
     edited
    -0.48
     EDIT
    -0.47
    .edit
    -0.46
     editing
    -0.45
    _EDIT
    -0.45
    -edit
    -0.45
    (edit
    -0.45
    _edit
    -0.44
    POSITIVE LOGITS
    ped
    0.30
    z
    0.28
    ropy
    0.27
    dz
    0.27
    ding
    0.27
    离
    0.26
    dra
    0.26
    ive
    0.25
    dm
    0.25
     Objective
    0.25
    Activations Density 0.032%

    No Known Activations