© 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. 30055
    Prev
    Next
    INDEX
    Explanations

    like

    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
    ties
    -0.28
    tim
    -0.26
     Ob
    -0.26
    "]==
    -0.26
    å®ŀäºĭ
    -0.25
    OVE
    -0.25
    tie
    -0.25
    %=
    -0.25
    /send
    -0.25
    lian
    -0.24
    POSITIVE LOGITS
    acebook
    0.26
    ä¹ĭåĬĽ
    0.25
    empor
    0.25
     kuk
    0.25
    umbo
    0.24
    seat
    0.24
    .place
    0.24
    åıĹçĽĬ
    0.24
    ä¼ģä¸ļåľ¨
    0.24
    å¤į
    0.24
    Activations Density 1.277%

    No Known Activations