© 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. 96251
    Prev
    Next
    INDEX
    Explanations

    speed

    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
    è¾ĥ为
    -0.26
    _lift
    -0.25
    rides
    -0.23
    /><
    -0.23
    ç¢
    -0.23
     fairly
    -0.23
    pragma
    -0.23
    Arrange
    -0.22
    <header
    -0.22
     Overs
    -0.22
    POSITIVE LOGITS
     speed
    1.48
    éĢŁåº¦
    1.40
    speed
    1.28
     speeds
    1.24
    éĢŁ
    1.23
    çļĦéĢŁåº¦
    1.23
     Speed
    1.20
    -speed
    1.18
    Speed
    1.16
    	speed
    1.14
    Activations Density 0.914%

    No Known Activations