© 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. 12-TRANSCODER-HP
    7. 23206
    Prev
    Next
    INDEX
    Explanations

    Mixed topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parm
    -0.29
     bound
    -0.27
    Parm
    -0.27
    eldon
    -0.27
    BOUND
    -0.26
     Bound
    -0.26
    çĸł
    -0.26
    æĬĹ
    -0.26
    heck
    -0.25
    iment
    -0.25
    POSITIVE LOGITS
    éŀĺ
    0.27
    owa
    0.26
    rove
    0.25
    ','%
    0.25
     %+
    0.25
     dew
    0.25
    rong
    0.24
    nets
    0.24
    æĬķå½±
    0.24
    prov
    0.24
    Activations Density 0.000%

    No Known Activations