© 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. 30-TRANSCODER-HP
    7. 96031
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -quarters
    -0.32
    quarters
    -0.32
     quarters
    -0.30
    _tokenize
    -0.29
    _HAL
    -0.28
    -quarter
    -0.27
    vero
    -0.26
    Dims
    -0.26
     hoping
    -0.25
     export
    -0.25
    POSITIVE LOGITS
    xDE
    0.27
    ucher
    0.26
    âĢ³
    0.26
     Crown
    0.24
    çŃĭ
    0.24
    强迫
    0.24
    ä¹ĺ
    0.24
    åı·
    0.24
    强åĪ¶
    0.24
     Enumeration
    0.24
    Activations Density 0.886%

    No Known Activations