© 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. 12-TRANSCODER-HP
    7. 23751
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eln
    -0.30
    DER
    -0.27
    Dll
    -0.26
    minecraft
    -0.26
    å¾·å°Ķ
    -0.25
    ÙĬات
    -0.25
    tü
    -0.25
    uckland
    -0.25
    Æ°a
    -0.25
     éc
    -0.24
    POSITIVE LOGITS
    æĪª
    0.30
     revolution
    0.27
    æĽĿåħī
    0.27
    é§IJ
    0.27
     exposure
    0.27
     p
    0.27
     fundamentally
    0.26
     agree
    0.26
     style
    0.25
     job
    0.25
    Activations Density 0.000%

    No Known Activations