© 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. 108379
    Prev
    Next
    INDEX
    Explanations

    to

    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
    åĪ°äºĨ
    -0.26
     settles
    -0.26
     Anchor
    -0.25
    ниÑĨ
    -0.25
    å¼Ģå±ķäºĨ
    -0.24
     settle
    -0.24
     Toolbox
    -0.24
    _include
    -0.23
    ResponseType
    -0.23
     rely
    -0.23
    POSITIVE LOGITS
     impl
    0.28
    onium
    0.28
     incentiv
    0.27
    (pat
    0.26
    è¯ģæĺİ
    0.26
    æ°¸
    0.25
    çIJĨ解åĴĮ
    0.25
    çĸı导
    0.24
    usch
    0.24
    pers
    0.24
    Activations Density 1.295%

    No Known Activations