© 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. 18639
    Prev
    Next
    INDEX
    Explanations

    residues

    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
    段
    -0.57
     segment
    -0.52
     section
    -0.52
    section
    -0.51
     segments
    -0.49
     sections
    -0.47
    éĥ¨åĪĨ
    -0.47
    segment
    -0.45
    parts
    -0.45
     element
    -0.45
    POSITIVE LOGITS
    lah
    0.28
     residue
    0.27
     tú
    0.27
     residues
    0.26
    _outputs
    0.25
    窦
    0.25
    æ®ĭ
    0.25
    idue
    0.24
    enerate
    0.24
    erville
    0.24
    Activations Density 15.438%

    No Known Activations