© 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. 107921
    Prev
    Next
    INDEX
    Explanations

    Code or configuration 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
    esser
    -0.27
    çe
    -0.26
    core
    -0.25
    éģµå®Ī
    -0.25
    åĪ¶åº¦
    -0.25
    æīĵå¾Ĺ
    -0.24
    使
    -0.24
    ãģªãģijãĤĮãģ°
    -0.24
    æ¸Ń
    -0.24
    ä¸īæĿ¡
    -0.23
    POSITIVE LOGITS
     capita
    0.29
    addin
    0.29
     debacle
    0.28
     theirs
    0.26
    ä¸ĭæĿ¥çļĦ
    0.26
    ocoa
    0.25
    -cap
    0.25
     zupeÅĤ
    0.25
    atif
    0.25
     hic
    0.24
    Activations Density 1.928%

    No Known Activations