© 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. 108693
    Prev
    Next
    INDEX
    Explanations

    various text snippets

    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
    amarin
    -0.27
    æ¯Ķè¾ĥé«ĺ
    -0.26
    åĩºçĶŁ
    -0.26
    å°Ĩè¾¾åĪ°
    -0.26
     оÑĤпÑĢав
    -0.25
    olid
    -0.25
     defaults
    -0.25
     inspected
    -0.24
    Mixed
    -0.24
    isoft
    -0.24
    POSITIVE LOGITS
    enze
    0.28
    edly
    0.25
     Bruce
    0.25
    .Of
    0.24
    å¿ĥ缮
    0.24
    å¿ĥ缮ä¸Ń
    0.23
     virtue
    0.23
    ].[
    0.23
     actress
    0.23
     gre
    0.23
    Activations Density 1.069%

    No Known Activations