© 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. 107043
    Prev
    Next
    INDEX
    Explanations

    Code or technical 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
    åijĬè¯ī她
    -0.29
    gue
    -0.28
    ãĤıãģŁ
    -0.27
    æĻ®
    -0.26
     transition
    -0.25
    enny
    -0.24
    åijĬè¯īä»ĸ
    -0.24
    Ñīен
    -0.24
    OPSIS
    -0.24
    å°½æĹ©
    -0.24
    POSITIVE LOGITS
     Bay
    0.28
    .codehaus
    0.28
    éĻ©
    0.28
    èĬ±
    0.28
    iese
    0.27
    ÑĢÑı
    0.26
    å½±
    0.26
    rov
    0.25
     bay
    0.24
    æĬĺ
    0.24
    Activations Density 1.092%

    No Known Activations