© 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. 27-TRANSCODER-HP
    7. 9198
    Prev
    Next
    INDEX
    Explanations

    dead/dying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.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¸Ģ次æĢ§
    -0.27
    åıªä¼ļ
    -0.27
    gings
    -0.27
    ä¹ŁæĹłæ³ķ
    -0.27
    ibilities
    -0.26
    å±ŀäºİèĩªå·±
    -0.26
    ä¹Łåıªæľī
    -0.25
    mium
    -0.25
    豫
    -0.25
    ìľł
    -0.25
    POSITIVE LOGITS
    ibaba
    0.25
    åģľçĶµ
    0.24
    SOR
    0.24
    neau
    0.24
    alf
    0.24
     municip
    0.24
    Lng
    0.24
    黣
    0.24
     einf
    0.24
     Synopsis
    0.24
    Activations Density 0.004%

    No Known Activations