© 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. 7385
    Prev
    Next
    INDEX
    Explanations

    "at least" or minimum

    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
    atown
    -0.26
    èģļ
    -0.26
    屦
    -0.25
    ensburg
    -0.25
    ten
    -0.25
    rust
    -0.24
    Ef
    -0.24
    altung
    -0.24
    -town
    -0.24
    ä¸Ĭãģ®
    -0.24
    POSITIVE LOGITS
     '{}'
    0.25
    å·§åIJĪ
    0.24
    å¸Ĥåľºç«ŀäºī
    0.24
    idl
    0.24
    Parms
    0.23
     –↵↵
    0.23
     gi
    0.23
     pregn
    0.23
     simply
    0.23
    仵
    0.23
    Activations Density 0.009%

    No Known Activations