© 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. 18505
    Prev
    Next
    INDEX
    Explanations

    Ok

    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
     ed
    -0.28
     upward
    -0.27
    ives
    -0.26
    cts
    -0.25
    ime
    -0.25
    sonian
    -0.25
    ķĮ
    -0.25
    ersonic
    -0.25
    }}>
    -0.25
     dev
    -0.24
    POSITIVE LOGITS
    å¢ŀåĢ¼
    0.31
    latent
    0.26
    åī¯
    0.25
    ikon
    0.25
    ·»
    0.25
    åij¨ãĤĬ
    0.25
     inout
    0.25
    .chain
    0.24
     separ
    0.24
     penis
    0.24
    Activations Density 0.005%

    No Known Activations