© 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. 19408
    Prev
    Next
    INDEX
    Explanations

    studies

    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
     prove
    -0.35
     proofs
    -0.33
    è¨
    -0.33
    è¯ģæĺİ
    -0.32
     proof
    -0.32
     proving
    -0.31
     proven
    -0.31
    -proof
    -0.30
     proves
    -0.29
     Proof
    -0.29
    POSITIVE LOGITS
     utilizing
    0.38
     using
    0.38
     found
    0.35
     on
    0.35
     employing
    0.32
    åł±
    0.30
    using
    0.30
     Using
    0.29
     seeking
    0.29
     based
    0.28
    Activations Density 1.907%

    No Known Activations