© 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. 142159
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    chter
    -0.25
    orgen
    -0.25
    icut
    -0.24
    è¯ĺ
    -0.24
    ubi
    -0.24
    ä¸ī代
    -0.23
    æİĸ
    -0.23
    >w
    -0.23
    eki
    -0.23
    ek
    -0.23
    POSITIVE LOGITS
    ç°ĭ
    0.25
    _ENABLED
    0.25
     yes
    0.25
    ãĥĭãĥ³ãĤ°
    0.25
    æľīéĹ®é¢ĺ
    0.24
    enburg
    0.24
    eses
    0.24
    讫
    0.23
     conc
    0.23
     ê·¸ëłĩ
    0.23
    Activations Density 3.852%

    No Known Activations