© 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. 108498
    Prev
    Next
    INDEX
    Explanations

    cart

    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
    è¬Ľ
    -0.27
    æī£
    -0.26
    ispers
    -0.26
     наз
    -0.25
    åĴ¨è¯¢
    -0.24
    plet
    -0.24
     ÑĨен
    -0.24
    çĵ´
    -0.24
    fers
    -0.23
    Alter
    -0.23
    POSITIVE LOGITS
    ographer
    0.33
    oon
    0.31
    ographers
    0.30
    ographic
    0.29
    ilage
    0.28
    /cart
    0.27
    oons
    0.26
    è¯ļæĦı
    0.26
    ographical
    0.26
    HEST
    0.26
    Activations Density 0.920%

    No Known Activations