© 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. 35-TRANSCODER-HP
    7. 40134
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çħĮ
    -0.27
     dazz
    -0.27
     hus
    -0.26
    adesh
    -0.26
     bez
    -0.25
    cycles
    -0.25
     nonetheless
    -0.25
     doses
    -0.25
     chambre
    -0.24
     slam
    -0.24
    POSITIVE LOGITS
    iw
    0.39
    inant
    0.34
    ing
    0.33
    iq
    0.33
    ingroup
    0.33
    inst
    0.32
    iy
    0.31
    ift
    0.31
    rant
    0.31
    iu
    0.30
    Activations Density 0.085%

    No Known Activations