© 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. 107797
    Prev
    Next
    INDEX
    Explanations

    Code and data records

    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
    å¤ĩ
    -0.29
    å¯Ĵ
    -0.28
    angers
    -0.27
    AMB
    -0.26
    باÙĨ
    -0.26
     grounds
    -0.25
     hs
    -0.24
    uby
    -0.24
     cade
    -0.24
     fore
    -0.23
    POSITIVE LOGITS
    scrollTop
    0.27
    èĩ³æѤ
    0.26
    èĩªç§°
    0.26
     воздейÑģÑĤв
    0.26
    leen
    0.25
    DOCTYPE
    0.24
     sinus
    0.24
     weighted
    0.24
    輩
    0.24
     UUID
    0.23
    Activations Density 0.153%

    No Known Activations