© 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. 42385
    Prev
    Next
    INDEX
    Explanations

    online text excerpts

    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
    ste
    -0.28
    eing
    -0.28
    å¸Į
    -0.27
     summarized
    -0.27
    umd
    -0.26
     ourselves
    -0.25
    edom
    -0.25
    çĽĴ
    -0.24
    fat
    -0.24
     ADDR
    -0.24
    POSITIVE LOGITS
     Bout
    0.28
    statt
    0.27
    grounds
    0.26
     offsetof
    0.26
     clashes
    0.26
     clash
    0.25
    èŀį
    0.25
    ÑħваÑĤ
    0.25
    unist
    0.25
    į
    0.24
    Activations Density 0.001%

    No Known Activations