© 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. 141220
    Prev
    Next
    INDEX
    Explanations

    ==

    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
     involved
    -0.26
     recruitment
    -0.25
     attachment
    -0.25
     execution
    -0.25
     bro
    -0.24
     pass
    -0.24
     executions
    -0.24
     predominant
    -0.23
     emb
    -0.23
    omin
    -0.22
    POSITIVE LOGITS
    ideo
    0.33
    æĹłç©·
    0.28
    æķij
    0.28
     Seeder
    0.28
    æĽ´æ·±
    0.27
    loth
    0.27
    æİĴ
    0.26
    ç»ı
    0.26
    éĢĶå¾Ħ
    0.25
    etheless
    0.24
    Activations Density 14.616%

    No Known Activations