© 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. 108699
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    aney
    -0.30
    embro
    -0.28
    endon
    -0.27
    ModelProperty
    -0.26
    vio
    -0.26
    STER
    -0.26
    aroo
    -0.26
    个åĪ«
    -0.25
    á»ī
    -0.25
    çĶ³
    -0.25
    POSITIVE LOGITS
    è¾Ĥ
    0.30
    tant
    0.30
    ism
    0.29
    ts
    0.29
    ../../../
    0.28
    tet
    0.26
    worm
    0.26
    tics
    0.25
    Connecting
    0.25
    shoot
    0.24
    Activations Density 0.950%

    No Known Activations