© 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. 8317
    Prev
    Next
    INDEX
    Explanations

    say articles

    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
    OURS
    -0.29
    ours
    -0.28
    èµĦæºIJéħįç½®
    -0.27
     intervening
    -0.27
    表æĺİ
    -0.27
    umat
    -0.26
    illery
    -0.26
     gums
    -0.26
    ledon
    -0.26
    ries
    -0.26
    POSITIVE LOGITS
    ä¸ŃåĽ½äººæ°ij
    0.28
    .bel
    0.27
     struggle
    0.27
    ä¸įå¤Ł
    0.26
     wo
    0.26
     unity
    0.26
     unwilling
    0.25
     willingness
    0.25
     how
    0.25
     dissatisfaction
    0.25
    Activations Density 0.006%

    No Known Activations