© 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. 31-TRANSCODER-HP
    7. 19476
    Prev
    Next
    INDEX
    Explanations

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°ij
    -0.50
    å¤ļ
    -0.43
     multi
    -0.35
    Multi
    -0.35
     mult
    -0.34
     Multi
    -0.34
    æĪĸå¤ļ
    -0.33
    太å°ij
    -0.33
    Little
    -0.32
    æľīå¤ļ
    -0.32
    POSITIVE LOGITS
     no
    0.36
    no
    0.33
    	no
    0.29
    No
    0.29
    NO
    0.29
    .no
    0.28
    _no
    0.28
    (no
    0.28
    _NO
    0.27
    .NO
    0.27
    Activations Density 0.786%

    No Known Activations