© 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. 57740
    Prev
    Next
    INDEX
    Explanations

    say "month of the year"

    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
    çµĦ
    -0.27
     Weeks
    -0.26
    styl
    -0.25
    åĩłä¸ªæľĪ
    -0.25
     unde
    -0.25
    åŁİå¸Ĥ建设
    -0.24
     thrust
    -0.24
    .Compile
    -0.24
    GetName
    -0.24
    çĺ¦
    -0.23
    POSITIVE LOGITS
    acio
    0.27
     IEnumerator
    0.26
    è¿Ļä¸ĢåĪ»
    0.25
    çĿ¦
    0.25
    erset
    0.25
    ritten
    0.24
    OperationException
    0.24
     beyond
    0.23
    æ°Ķ
    0.23
    ª
    0.23
    Activations Density 0.004%

    No Known Activations