© 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. 19415
    Prev
    Next
    INDEX
    Explanations

    inclusion

    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
    ounces
    -0.27
    å°½åı¯èĥ½
    -0.26
    论
    -0.26
    æįħ
    -0.25
    秤
    -0.25
    .left
    -0.25
     Nah
    -0.25
    ÑĢÑĥÑĪ
    -0.25
    left
    -0.24
    å°½éĩı
    -0.24
    POSITIVE LOGITS
     featured
    0.44
     included
    0.40
     incorporated
    0.36
     contained
    0.35
     embedded
    0.32
     displayed
    0.32
     Included
    0.31
    featured
    0.30
     showcased
    0.30
     integrated
    0.30
    Activations Density 0.647%

    No Known Activations