© 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. 54242
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
     cub
    -0.32
    odings
    -0.28
     comm
    -0.25
    æį¢
    -0.25
    lear
    -0.25
    æıĽ
    -0.24
    å³Ħ
    -0.24
     prov
    -0.24
     leaps
    -0.23
     arch
    -0.23
    POSITIVE LOGITS
    ArrayOf
    0.28
    tbody
    0.28
    ÈĻ
    0.27
    t
    0.26
    -tr
    0.26
    chet
    0.25
    IEEE
    0.25
    ï½Ķ
    0.24
    jad
    0.24
    alc
    0.24
    Activations Density 0.004%

    No Known Activations