© 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. 108578
    Prev
    Next
    INDEX
    Explanations

    Ambiguity/Uncertainty

    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
    Bs
    -0.28
     ÑħозÑıй
    -0.28
    çĶŁæ´»ä¹łæĥ¯
    -0.25
    ctime
    -0.25
    vs
    -0.25
    å§Ķç»Ħç»ĩ
    -0.24
    å§Ķåijĺ
    -0.23
     CASE
    -0.23
    é«Ģ
    -0.23
    å¡į
    -0.23
    POSITIVE LOGITS
    ories
    0.33
    ably
    0.31
    代
    0.28
    ement
    0.27
    unity
    0.27
    åĪĨæĺİ
    0.27
    å½±
    0.26
    IFIED
    0.26
    imately
    0.26
    åı¯æĥ³èĢĮçŁ¥
    0.25
    Activations Density 0.971%

    No Known Activations