© 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. 32-TRANSCODER-HP
    7. 43442
    Prev
    Next
    INDEX
    Explanations

    programming/data files context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Tx
    -0.30
    arro
    -0.29
    orsch
    -0.29
     sher
    -0.27
    asha
    -0.27
    sh
    -0.27
     Yup
    -0.26
    çIJĥ
    -0.26
     prediction
    -0.26
    alin
    -0.26
    POSITIVE LOGITS
    äºĶä¸Ģ
    0.27
    ubits
    0.27
     кан
    0.26
    theid
    0.25
    çĽį
    0.25
    สà¸Ķ
    0.25
    ival
    0.25
    æ´»
    0.24
     dresser
    0.24
    IXEL
    0.24
    Activations Density 0.005%

    No Known Activations