© 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. 19319
    Prev
    Next
    INDEX
    Explanations

    trans

    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
    lijk
    -0.30
     setMessage
    -0.27
    ActionTypes
    -0.26
    огÑĢам
    -0.26
    kos
    -0.25
     sek
    -0.25
    ValueCollection
    -0.24
    夹
    -0.24
    ä¹IJ
    -0.24
    lik
    -0.24
    POSITIVE LOGITS
    æĦŁæŁĵ
    0.43
     Inf
    0.41
     inf
    0.41
    Inf
    0.41
    inf
    0.40
     infection
    0.40
    ä¼łæŁĵ
    0.40
     infectious
    0.40
    _inf
    0.39
     INF
    0.38
    Activations Density 0.798%

    No Known Activations