© 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. 63105
    Prev
    Next
    INDEX
    Explanations

    church

    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
    esome
    -0.27
    åĪĻæĺ¯
    -0.27
    Aceptar
    -0.26
    pars
    -0.26
     æĿ
    -0.26
    '),'
    -0.25
     вÑģÑĤÑĢ
    -0.25
    .old
    -0.25
     NW
    -0.25
    éĤĵå°ı
    -0.24
    POSITIVE LOGITS
    sson
    0.25
    ä¸Ģä½ĵ
    0.25
    èµī
    0.24
    uries
    0.24
    éľ²åĩº
    0.23
    好å¤Ħ
    0.23
    ä¸ĢåıĮ
    0.23
    eil
    0.23
    eness
    0.23
    elib
    0.23
    Activations Density 7.180%

    No Known Activations