© 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. 88464
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
    å©Ģ
    -0.27
    ghi
    -0.26
     scor
    -0.26
    ãĤ·ãĥ¼ãĤºãĥ³
    -0.26
    ipient
    -0.26
    chai
    -0.26
    chs
    -0.25
    itura
    -0.25
     bard
    -0.25
    acements
    -0.24
    POSITIVE LOGITS
     dm
    0.26
     significantly
    0.25
     requests
    0.24
     CK
    0.24
    åįģä¸īäºĶ
    0.24
    icense
    0.24
    eworld
    0.24
    .addTab
    0.23
    åĩĢåľŁ
    0.23
    ussy
    0.23
    Activations Density 0.005%

    No Known Activations