© 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. 150951
    Prev
    Next
    INDEX
    Explanations

    News articles about events

    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
     #$
    -0.28
     avoided
    -0.28
    æ¿ĢçĥĪçļĦ
    -0.27
    UDIO
    -0.27
    pure
    -0.26
     PURE
    -0.26
     preceded
    -0.25
    -buy
    -0.25
    åıijçĶŁåľ¨
    -0.24
    udio
    -0.24
    POSITIVE LOGITS
    caff
    0.29
    èµĦæĸĻ
    0.26
    onz
    0.26
    MOTE
    0.25
    çļĦè·Ŀ离
    0.25
    çļĦä¼ģä¸ļ
    0.24
    unas
    0.24
    Å¡e
    0.24
    ORN
    0.24
    èºģ
    0.24
    Activations Density 0.917%

    No Known Activations