© 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. 22-TRANSCODER-HP
    7. 112411
    Prev
    Next
    INDEX
    Explanations

    Bible verses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inc
    -0.31
     Boundary
    -0.29
     free
    -0.27
    ITIES
    -0.26
    rys
    -0.26
     Border
    -0.26
    èĩªçĶ±
    -0.25
    ãĤĮ
    -0.25
    ys
    -0.24
    dev
    -0.24
    POSITIVE LOGITS
     thereof
    0.27
    åĪĨä¼ļ
    0.27
    hoot
    0.27
    oped
    0.27
    çĿ¡åīį
    0.26
    flate
    0.25
    ensively
    0.25
    æĴ·
    0.24
    hdr
    0.24
    çĴ§
    0.24
    Activations Density 0.002%

    No Known Activations