© 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. 23-TRANSCODER-HP
    7. 25118
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    忤
    -0.27
     ...↵↵↵↵
    -0.27
    çĶļèĩ³æĺ¯
    -0.27
    ä¾ĿéĿł
    -0.26
    éļĶ
    -0.26
    çĶļèĩ³
    -0.25
     even
    -0.25
    ãĤĭãģ®ãģ§
    -0.25
    æĭĽ
    -0.25
    ').
    -0.24
    POSITIVE LOGITS
    ä¼ģä¸ļåĴĮ
    0.26
     geme
    0.25
     racked
    0.25
     Everywhere
    0.25
    fg
    0.25
    ecs
    0.24
    gew
    0.24
    æľīçļĦ人
    0.24
    onder
    0.24
    ecc
    0.24
    Activations Density 0.007%

    No Known Activations