© 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. 9-TRANSCODER-HP
    7. 30023
    Prev
    Next
    INDEX
    Explanations

    wish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı¶
    -0.30
     wished
    -0.30
     wishes
    -0.29
    uba
    -0.29
    toast
    -0.27
    goog
    -0.27
    ington
    -0.25
    羣çĪ±
    -0.25
    èĭ¥æĤ¨
    -0.25
    ivals
    -0.24
    POSITIVE LOGITS
    enance
    0.28
    å«Įçĸij
    0.28
    沤
    0.26
    è¦ģåıĬæŶ
    0.25
    bir
    0.25
    Explore
    0.25
    elta
    0.25
    笼
    0.24
    çĽĺæ´»
    0.24
     Gambling
    0.23
    Activations Density 2.001%

    No Known Activations