© 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. 30-TRANSCODER-HP
    7. 95728
    Prev
    Next
    INDEX
    Explanations

    tissue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COND
    -0.31
    hx
    -0.28
    çĵ®
    -0.27
    ç´łè´¨æķĻèĤ²
    -0.25
    _HAL
    -0.25
    parts
    -0.25
    ç´łæĿIJ
    -0.25
    atorium
    -0.24
    åºĬ
    -0.24
     POV
    -0.24
    POSITIVE LOGITS
    æ°´
    0.30
    çģ°
    0.29
     water
    0.29
     gre
    0.28
    crets
    0.27
    TAG
    0.27
    é¡į
    0.26
     apr
    0.25
    OMEM
    0.25
    etas
    0.24
    Activations Density 0.003%

    No Known Activations