© 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. 31-TRANSCODER-HP
    7. 18797
    Prev
    Next
    INDEX
    Explanations

    ros

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åłµå¡ŀ
    -0.30
    gel
    -0.27
    ç®į
    -0.27
    algo
    -0.27
    æĻ¶
    -0.26
     Moff
    -0.26
    OPT
    -0.25
    å§ľ
    -0.25
     ngh
    -0.25
     crystals
    -0.24
    POSITIVE LOGITS
     Ros
    0.31
    armed
    0.28
    ÑĢоз
    0.27
     stamp
    0.26
     oz
    0.26
    airs
    0.26
     unten
    0.26
    ODE
    0.26
    Ros
    0.26
    ç°¿
    0.25
    Activations Density 0.010%

    No Known Activations