© 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. 108613
    Prev
    Next
    INDEX
    Explanations

    2

    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
    fork
    -0.27
     sight
    -0.27
    åıĪæľī
    -0.26
    olly
    -0.26
    aly
    -0.26
     Chall
    -0.26
    éĩĩåıĸ
    -0.25
    æīĵæĬĺ
    -0.25
    quina
    -0.25
    交åıī
    -0.25
    POSITIVE LOGITS
    éģįåıĬ
    0.28
     ['#
    0.27
    @Module
    0.26
    parable
    0.26
    åı¯éĿłçļĦ
    0.26
    ypy
    0.26
    严éĩįçļĦ
    0.25
    åĵĮ
    0.25
     effective
    0.25
    uteur
    0.24
    Activations Density 1.971%

    No Known Activations