© 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. 57308
    Prev
    Next
    INDEX
    Explanations

    technical/code-related texts

    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
    пон
    -0.31
    benh
    -0.26
    æ³±
    -0.26
    ä¸į认è¯Ĩ
    -0.25
    çIJĨäºĭ
    -0.24
    ÑĭÑĪ
    -0.24
    icontains
    -0.24
    pré
    -0.24
    ledon
    -0.24
    sut
    -0.24
    POSITIVE LOGITS
    为
    0.52
    çĤº
    0.46
    åĿĩ为
    0.33
    ä¸Ģ个æĺ¯
    0.32
    æĺ¯
    0.32
    çĪ²
    0.32
    究竣æĺ¯
    0.32
    ä¹ĥ
    0.31
     being
    0.30
    æĺ¯éŁ©åĽ½
    0.30
    Activations Density 0.004%

    No Known Activations