© 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. 5080
    Prev
    Next
    INDEX
    Explanations

    potentially threatening/serious

    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
    edo
    -0.28
    YPE
    -0.26
    IENT
    -0.25
    eded
    -0.24
     experimental
    -0.24
    ansas
    -0.24
     routes
    -0.24
    æľīä»»ä½ķ
    -0.24
    æĹłè®º
    -0.24
    å¾®
    -0.23
    POSITIVE LOGITS
     costly
    0.28
    anni
    0.27
    大象
    0.26
    æīĵéĢłæĪIJ
    0.26
    -li
    0.25
    çªŁ
    0.24
    @d
    0.24
    omial
    0.24
    metis
    0.24
    åģļè¿ĩ
    0.23
    Activations Density 0.015%

    No Known Activations