© 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. 33-TRANSCODER-HP
    7. 53625
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīįè¡Į
    -0.28
    icum
    -0.27
     PACKET
    -0.26
    Ｋ
    -0.26
    æ·ŀ
    -0.26
    ï¼·
    -0.25
    积æŀģåıĤä¸İ
    -0.25
    å®īåħ¨ä¿Ŀéļľ
    -0.24
    OPY
    -0.24
    社群
    -0.24
    POSITIVE LOGITS
    åľ°
    0.35
    Ãł
    0.30
     ground
    0.30
    .
    0.29
    G
    0.29
    g
    0.29
     G
    0.28
    ,
    0.28
    á
    0.28
    My
    0.28
    Activations Density 0.005%

    No Known Activations