© 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. 22-TRANSCODER-HP
    7. 112460
    Prev
    Next
    INDEX
    Explanations

    journal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é«ĺæĺĤ
    -0.27
    æ´ģçĻ½
    -0.26
    ãĥ¼ãĥł
    -0.25
    ewire
    -0.23
     slideshow
    -0.23
     arrays
    -0.23
    å¤ļ项
    -0.23
    opaque
    -0.23
    ete
    -0.22
    alent
    -0.22
    POSITIVE LOGITS
    è³ŀ
    0.27
     каÑĩ
    0.25
    åĪĬ
    0.25
    å¤ĸç§ij
    0.25
    åĴĮåľ°åĮº
    0.24
    antz
    0.24
     contrario
    0.24
    å®Ŀ
    0.24
    >NN
    0.24
     Chemistry
    0.24
    Activations Density 0.021%

    No Known Activations