© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6934
    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_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tang
    -0.28
    åİ¢
    -0.26
    åħ³éŨ
    -0.26
    DET
    -0.26
    apon
    -0.25
    çIJIJ
    -0.25
    éģĩè§ģ
    -0.24
     extrem
    -0.24
    æĥħå½¢
    -0.24
    ipment
    -0.23
    POSITIVE LOGITS
    /apache
    0.28
    åŃļ
    0.25
    æĦı大
    0.25
    зол
    0.25
    æĽ´å¥½çļĦ
    0.24
     volte
    0.24
    éĿ©åij½
    0.23
    çĥĻ
    0.23
    åį°è®°
    0.23
    senal
    0.23
    Activations Density 0.004%

    No Known Activations