© 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. 24154
    Prev
    Next
    INDEX
    Explanations

    online instructions/technical content

    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
    erne
    -0.25
    chants
    -0.25
    achten
    -0.23
    Tour
    -0.22
    ç»ŀ
    -0.22
    ä¸ĢèĪ¬
    -0.21
    XmlNode
    -0.21
    otate
    -0.21
     Tu
    -0.21
    rar
    -0.21
    POSITIVE LOGITS
    以便
    0.85
     ÑĩÑĤобÑĭ
    0.75
    以åħį
    0.72
    è¿Ļæł·æīįèĥ½
    0.72
     afin
    0.67
    æĺ¯ä¸ºäºĨ
    0.63
     Äijá»ĥ
    0.60
     lest
    0.59
    å°±æĺ¯ä¸ºäºĨ
    0.57
    为äºĨ
    0.56
    Activations Density 0.004%

    No Known Activations