© 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. 22-TRANSCODER-HP
    7. 111486
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agos
    -0.30
    )_
    -0.27
    ÑĨи
    -0.26
    mares
    -0.26
    )__
    -0.25
    çĶ¨èĩªå·±çļĦ
    -0.25
     Closing
    -0.24
    оÑģÑĮ
    -0.24
    idan
    -0.23
    .quality
    -0.23
    POSITIVE LOGITS
    descending
    0.28
     little
    0.26
    =""><
    0.26
    æĥ¯ä¾ĭ
    0.25
    .FloatTensor
    0.24
    åĵªå®¶
    0.24
    éĢļçŁ¥ä¹¦
    0.23
    åĵªä¸Ģ个
    0.23
    è·Łä½ł
    0.23
     denounced
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.