© 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. 24-TRANSCODER-HP
    7. 151030
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unbe
    -0.27
     quelque
    -0.26
    	CHECK
    -0.24
    ****↵
    -0.23
    æŁIJç§į
    -0.23
    æŁIJä¸Ģ
    -0.23
    æŁIJ
    -0.23
     checkout
    -0.23
    adamente
    -0.23
    prene
    -0.23
    POSITIVE LOGITS
    èĤĩ
    0.29
    è¯Ń
    0.28
    ORIZATION
    0.28
    è´§å¸ģ
    0.27
     orth
    0.27
    åŃĹåı·
    0.27
    èªŀ
    0.26
    -language
    0.26
    ocument
    0.25
    -ev
    0.25
    Activations Density 0.128%

    No Known Activations