© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    de

    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
    åİĨå¹´
    -0.27
    临æŶ
    -0.26
    psz
    -0.25
    ä½įæĸ¼
    -0.25
    upos
    -0.25
     Temp
    -0.25
    éļıä¹ĭ
    -0.24
     omin
    -0.24
    erra
    -0.24
    _binary
    -0.24
    POSITIVE LOGITS
     administration
    0.30
    matter
    0.28
    客
    0.28
     matter
    0.28
     Administration
    0.27
    Handled
    0.27
    伺
    0.27
    xlim
    0.27
     issue
    0.26
    strength
    0.26
    Activations Density 0.007%

    No Known Activations