© 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. 30020
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     hourly
    -0.28
    Ease
    -0.27
    ease
    -0.27
    asy
    -0.26
    /person
    -0.26
    CONNECT
    -0.25
    pain
    -0.24
    istle
    -0.24
    oose
    -0.24
    oval
    -0.24
    POSITIVE LOGITS
    æľĢé«ĺçļĦ
    0.27
    ä¼°
    0.26
     responsable
    0.26
     Relevant
    0.25
    dsp
    0.25
    aj
    0.25
    æ²ĥ
    0.24
    ëĭ¨
    0.24
     irrelevant
    0.24
     relevant
    0.24
    Activations Density 1.035%

    No Known Activations