© 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. 52932
    Prev
    Next
    INDEX
    Explanations

    Computer code

    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
     Following
    -0.28
    ..↵
    -0.26
     characterize
    -0.24
    å½¢
    -0.24
    å¦Ĩ
    -0.24
     foliage
    -0.24
    çīĮ
    -0.24
    енÑĮ
    -0.24
    .\
    -0.24
     ARG
    -0.24
    POSITIVE LOGITS
     Ment
    0.30
    !";č↵
    0.27
    č
    0.27
    æĸĻ
    0.25
    ave
    0.25
    illy
    0.24
    !č↵
    0.24
    ess
    0.24
     ".$_
    0.24
    jack
    0.24
    Activations Density 0.051%

    No Known Activations