© 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. 22-TRANSCODER-HP
    7. 88218
    Prev
    Next
    INDEX
    Explanations

    And

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shall
    -0.27
     hence
    -0.26
     therefore
    -0.26
     afterwards
    -0.26
     thereafter
    -0.26
    ãĬĹ
    -0.25
    åĽłæѤ
    -0.25
     thus
    -0.25
     afterward
    -0.25
    èĬĤ
    -0.25
    POSITIVE LOGITS
     hott
    0.26
    devil
    0.26
    éļ¾æĢª
    0.25
    oret
    0.25
    ooth
    0.25
    è§ĤæľĽ
    0.25
    FRING
    0.24
    amic
    0.24
    енÑĤа
    0.24
    ensation
    0.24
    Activations Density 0.006%

    No Known Activations