© 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. 19-TRANSCODER-HP
    7. 8588
    Prev
    Next
    INDEX
    Explanations

    Code related

    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
    mát
    -0.27
    ĸī
    -0.27
    drink
    -0.27
    åĸĿ
    -0.26
    åģ·åģ·
    -0.25
    çĶ¨éĢĶ
    -0.25
    OrCreate
    -0.24
    åĸĿæ°´
    -0.24
    NZ
    -0.24
    éĩįè§Ĩ
    -0.24
    POSITIVE LOGITS
    以èī²
    0.28
     ache
    0.27
    enor
    0.27
    æĮĩçĶ²
    0.26
     Sterling
    0.26
    STER
    0.25
    ries
    0.25
    ä¼´
    0.24
    aus
    0.24
    oud
    0.24
    Activations Density 0.010%

    No Known Activations