© 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. 7014
    Prev
    Next
    INDEX
    Explanations

    elevation

    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
    ’ex
    -0.29
    æ´»çĿĢ
    -0.27
    æĹ¢æĺ¯
    -0.26
    并äºİ
    -0.26
    并ä¸İ
    -0.26
     Fence
    -0.26
     starred
    -0.25
    祺
    -0.25
     martyr
    -0.24
    /classes
    -0.24
    POSITIVE LOGITS
     cann
    0.28
    åĩłåįĥ
    0.28
     Muslim
    0.25
    )[:
    0.25
    伪
    0.24
     roles
    0.24
    åį
    0.24
     Islam
    0.24
    éĤij
    0.23
    isia
    0.23
    Activations Density 0.007%

    No Known Activations