© 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. 57464
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     influence
    -0.31
    å½±åĵį
    -0.30
    Impact
    -0.27
     Influence
    -0.27
     impact
    -0.27
    à¹ģà¸ļ
    -0.26
    impact
    -0.25
     Impact
    -0.25
    å½±åĵįåĬĽçļĦ
    -0.25
    æľºä¼ļ
    -0.25
    POSITIVE LOGITS
    stands
    0.25
    åĽ°
    0.25
    ä¸įè¿ĩ
    0.24
    以为
    0.24
    èī°è¾Ľ
    0.23
    yle
    0.23
    abric
    0.23
    ("'
    0.23
     nights
    0.23
     pot
    0.23
    Activations Density 0.013%

    No Known Activations