© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4860
    Prev
    Next
    INDEX
    Explanations

    depression

    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
    è¿Ļä¸ĢçĤ¹
    -0.27
    feit
    -0.25
     trenches
    -0.24
    大äºĭ
    -0.24
    å°ıäºĭ
    -0.23
     tern
    -0.23
    ä¸įç¦ģ
    -0.23
    åıĺéĢŁç®±
    -0.23
    åıªæĥ³
    -0.23
    .splitext
    -0.23
    POSITIVE LOGITS
     GK
    0.29
    ohl
    0.25
    utches
    0.24
     Lev
    0.24
     lips
    0.23
    HEMA
    0.23
     occurring
    0.22
    ike
    0.22
    SES
    0.22
    .snp
    0.22
    Activations Density 2.636%

    No Known Activations