© 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. 108577
    Prev
    Next
    INDEX
    Explanations

    additional information

    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
    odate
    -0.28
    perator
    -0.27
    izr
    -0.25
    -cur
    -0.25
    interop
    -0.25
    .generated
    -0.25
     masturbation
    -0.25
    ieved
    -0.25
    warts
    -0.24
     ÑĤоÑĢÑĢенÑĤ
    -0.24
    POSITIVE LOGITS
     the
    0.31
     there
    0.30
    åIJįåı«
    0.30
    ä½ıåľ¨
    0.30
     Fields
    0.29
    æľīä¸Ģä½į
    0.28
    é²į
    0.27
     I
    0.27
    æŶ任
    0.27
     M
    0.27
    Activations Density 0.954%

    No Known Activations