© 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. 19-TRANSCODER-HP
    7. 8935
    Prev
    Next
    INDEX
    Explanations

    movement and rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çģµæ´»
    -0.28
    å±¥è¡Į
    -0.27
    è¿IJ转
    -0.26
     umie
    -0.25
     clicked
    -0.25
    ç»´æĮģ
    -0.24
    allah
    -0.24
    å®ļæŶ
    -0.24
    åł¤
    -0.24
    stown
    -0.24
    POSITIVE LOGITS
    åĢĴ
    0.30
    æĬ¤èº«
    0.27
     disap
    0.26
    reverse
    0.25
     жÑĥÑĢнал
    0.25
    irts
    0.25
     reverse
    0.24
    StringEncoding
    0.24
    inis
    0.24
    ìħĶ
    0.24
    Activations Density 0.061%

    No Known Activations