© 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. 27-TRANSCODER-HP
    7. 56872
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ£
    -0.25
    usal
    -0.25
     undisclosed
    -0.24
    arden
    -0.24
     interpretation
    -0.24
    (chart
    -0.23
     Undert
    -0.23
     hảo
    -0.23
    æķ´æĶ¹æݪæĸ½
    -0.23
    -testid
    -0.23
    POSITIVE LOGITS
    ä½į
    0.28
    IDAD
    0.27
    å½ĵä½ł
    0.24
     Homo
    0.24
    ä¿İ
    0.23
    ÅĽci
    0.23
    æĸĩåĮĸ
    0.23
    oop
    0.23
    羨
    0.23
    ÐŃ
    0.23
    Activations Density 0.205%

    No Known Activations