© 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. 130321
    Prev
    Next
    INDEX
    Explanations

    Complex long-form text

    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
    ikon
    -0.29
    ullet
    -0.27
     coal
    -0.27
    exion
    -0.26
     poss
    -0.25
    Fcn
    -0.24
     oz
    -0.24
     Ñģмог
    -0.24
     clip
    -0.24
    lib
    -0.23
    POSITIVE LOGITS
    å´©æºĥ
    0.31
    hani
    0.30
    å¡ŀ
    0.30
    èĭį
    0.27
    antine
    0.26
     charg
    0.25
    弥补
    0.25
    .Std
    0.25
    bservable
    0.25
    le
    0.24
    Activations Density 62.087%

    No Known Activations