© 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. 108141
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ffffff
    -0.28
    ä»įçĦ¶æĺ¯
    -0.27
    ä¸įå¾Ĺ转载
    -0.26
    åľĪ
    -0.25
    arius
    -0.24
    fds
    -0.24
    lane
    -0.24
    çĸĻ
    -0.24
     resort
    -0.24
    æķĪæŀľåĽ¾
    -0.24
    POSITIVE LOGITS
    ne
    0.26
    ÑģÑĤÑĢой
    0.26
    涯
    0.25
    yat
    0.25
    å¸Ŀ
    0.25
     **
    0.25
    nee
    0.24
    вой
    0.24
    vit
    0.24
    ä¸ĢéŨ
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.