© 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. 41469
    Prev
    Next
    INDEX
    Explanations

    be

    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
     senses
    -0.26
    çijĻ
    -0.25
    onaut
    -0.25
    åŁºäºİ
    -0.24
    åĽ½ä¼ļ
    -0.24
    immers
    -0.24
     culpa
    -0.24
    ä¿¡èªī
    -0.24
    unga
    -0.24
    强迫
    -0.23
    POSITIVE LOGITS
     ze
    0.28
     er
    0.28
    raise
    0.26
     led
    0.26
    ade
    0.25
    adic
    0.25
     le
    0.24
     erb
    0.24
     agent
    0.24
    elyn
    0.24
    Activations Density 0.002%

    No Known Activations