© 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. 22-TRANSCODER-HP
    7. 88469
    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_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įæ¸ħæ¥ļ
    -0.29
    ycl
    -0.27
    ä½łè§īå¾Ĺ
    -0.27
    çİ°æľī
    -0.26
    SCP
    -0.25
    iloc
    -0.25
     existing
    -0.25
     Existing
    -0.24
     unclear
    -0.24
    çİ°æľīçļĦ
    -0.24
    POSITIVE LOGITS
    èĩªå·±
    0.27
    åľ¨æķ´ä¸ª
    0.25
    [str
    0.25
     listened
    0.24
    aurus
    0.24
    dek
    0.24
    AllowAnonymous
    0.24
     listens
    0.24
    pillar
    0.24
     listener
    0.24
    Activations Density 0.005%

    No Known Activations