© 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. 20-TRANSCODER-HP
    7. 129693
    Prev
    Next
    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    天
    -0.27
    夫
    -0.27
    udio
    -0.26
    èħ°
    -0.25
    ách
    -0.24
     Spec
    -0.24
    /pub
    -0.23
    unc
    -0.23
    åıĭ
    -0.23
    ç»®
    -0.22
    POSITIVE LOGITS
    cycl
    0.31
    tera
    0.27
    LEMENT
    0.27
     SHR
    0.26
    avn
    0.25
    asn
    0.25
    ynos
    0.25
    —for
    0.25
    asil
    0.25
    gf
    0.24
    Activations Density 8.873%

    No Known Activations