© 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. 53153
    Prev
    Next
    INDEX
    Explanations

    primates/animals

    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
    ä½ĵ
    -0.31
    _GU
    -0.28
    ombo
    -0.28
    ures
    -0.27
    ideshow
    -0.27
    ãģĽ
    -0.27
     thủ
    -0.27
    iÅŁ
    -0.26
    еÑģп
    -0.26
    smith
    -0.25
    POSITIVE LOGITS
    oldt
    0.28
     poil
    0.24
     prac
    0.24
     Cov
    0.24
    glob
    0.24
     imag
    0.24
    oundation
    0.24
    çݰ代åĮĸ
    0.23
     globally
    0.23
    aily
    0.23
    Activations Density 0.013%

    No Known Activations