© 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. 32-TRANSCODER-HP
    7. 42809
    Prev
    Next
    INDEX
    Explanations

    microscopy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worthy
    -0.32
    欲
    -0.28
    urse
    -0.28
    è¤IJ
    -0.28
     кваÑĢÑĤиÑĢ
    -0.28
    å±ħ
    -0.27
    embr
    -0.26
    åĩĨåĪĻ
    -0.25
    OpenHelper
    -0.25
    ervoir
    -0.25
    POSITIVE LOGITS
     pin
    0.31
    osten
    0.28
    xin
    0.27
    aired
    0.27
    æĢ»åħ±
    0.26
    عÙĬÙĨ
    0.26
    uin
    0.26
     micro
    0.25
    ansson
    0.25
    pin
    0.25
    Activations Density 0.005%

    No Known Activations