© 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. 25-TRANSCODER-HP
    7. 108160
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æļĸæ°Ķ
    -0.28
     cellul
    -0.26
    çĶ¥
    -0.25
     localVar
    -0.25
    Lens
    -0.25
     encyclopedia
    -0.25
     choke
    -0.25
    icone
    -0.24
    é½Ĵ
    -0.24
    ce
    -0.24
    POSITIVE LOGITS
    çĽ¼æľĽ
    0.28
    ä¸Ģè·¯
    0.26
    å°±è¡ĮäºĨ
    0.25
    ickerView
    0.25
    å°±è¡Į
    0.24
    called
    0.23
    çļĦäºĭæĥħ
    0.23
    idor
    0.23
    ä½ıåľ¨
    0.23
     called
    0.23
    Activations Density 1.248%

    No Known Activations