© 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. 150134
    Prev
    Next
    INDEX
    Explanations

    upon

    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
     Post
    -0.28
    ideo
    -0.28
    -looking
    -0.27
     Overall
    -0.26
    Overall
    -0.26
     post
    -0.26
    /sdk
    -0.26
    ä¸ĢåĪĩéĥ½
    -0.26
     Pay
    -0.25
    çļĦæķ´ä½ĵ
    -0.25
    POSITIVE LOGITS
    antic
    0.25
    uder
    0.24
    æľĢå°ı
    0.24
    stag
    0.24
    {x
    0.23
     vale
    0.23
    earer
    0.23
    opleft
    0.23
    ksen
    0.23
    agle
    0.23
    Activations Density 0.106%

    No Known Activations