© 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. 8695
    Prev
    Next
    INDEX
    Explanations

    Code/non-English strings

    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
     repeats
    -0.26
    idy
    -0.25
    ome
    -0.25
    æ°ijéĹ´
    -0.25
     famously
    -0.25
     recurrent
    -0.25
     Require
    -0.25
     needy
    -0.25
    avy
    -0.24
    éķ¿å¾Ĺ
    -0.24
    POSITIVE LOGITS
    izzazione
    0.25
    -gl
    0.25
     FRAME
    0.25
    ĺ认
    0.25
     Ug
    0.25
    ìĭ±
    0.24
    帷
    0.24
    :mm
    0.24
    ê°ĢëĬĶ
    0.24
    dataTable
    0.24
    Activations Density 0.000%

    No Known Activations