© 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. 108372
    Prev
    Next
    INDEX
    Explanations

    at

    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
    atum
    -0.27
    æıIJ
    -0.26
    iz
    -0.26
    æ»ļçIJĥ
    -0.25
    it
    -0.25
    å¸IJ
    -0.25
    atu
    -0.24
    çİĩè¾¾
    -0.24
    strom
    -0.24
    .–
    -0.23
    POSITIVE LOGITS
    ory
    0.30
    ORY
    0.29
     earned
    0.27
    iates
    0.27
    uger
    0.26
     dec
    0.26
    TextColor
    0.25
     Decoration
    0.25
    emed
    0.25
    ergy
    0.25
    Activations Density 0.077%

    No Known Activations