© 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. 54011
    Prev
    Next
    INDEX
    Explanations

    angle

    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
    åĿĢ
    -0.24
    趺
    -0.23
    TextStyle
    -0.23
     funded
    -0.23
    mag
    -0.23
    身
    -0.23
    itter
    -0.23
    abbr
    -0.23
    oral
    -0.23
    迪士
    -0.22
    POSITIVE LOGITS
     angles
    0.84
     angle
    0.77
    è§Ĵ度
    0.76
     Angle
    0.62
    angle
    0.60
    Angle
    0.59
    (angle
    0.59
    angles
    0.58
     dimensions
    0.57
    è§Ĵ
    0.57
    Activations Density 0.206%

    No Known Activations