© 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. 108158
    Prev
    Next
    INDEX
    Explanations

    foreign language/encoding issues

    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
    point
    -0.26
     Exc
    -0.26
    iÄį
    -0.25
    建æĪIJåIJİ
    -0.25
     Habit
    -0.25
    xda
    -0.25
     Projection
    -0.25
    nant
    -0.25
     Construction
    -0.25
    æ°¸ä¹ħ
    -0.25
    POSITIVE LOGITS
    lrt
    0.26
    aney
    0.25
    ĵį
    0.24
    lator
    0.24
    大æ´ĭ
    0.23
    èĵ¬
    0.23
     clap
    0.23
     nas
    0.23
    çĶ©
    0.23
     tracks
    0.23
    Activations Density 0.887%

    No Known Activations