© 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. 8597
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific content

    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
     HBO
    -0.28
    åİĦ
    -0.25
     delic
    -0.25
    ä¸Ģ件äºĭ
    -0.24
    kor
    -0.24
    åĴĢ
    -0.24
    åİ»åĵªéĩĮ
    -0.24
    newInstance
    -0.24
    鬼
    -0.24
     Perfect
    -0.24
    POSITIVE LOGITS
    oves
    0.26
    munition
    0.26
    éĺ¶æ®µ
    0.25
    adiator
    0.25
    _cats
    0.25
    -duration
    0.24
    ervo
    0.24
     behind
    0.24
     Stage
    0.24
    æľºæ¢°
    0.24
    Activations Density 0.000%

    No Known Activations