© 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. 53641
    Prev
    Next
    INDEX
    Explanations

    Code, research, clinical trials

    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
     Sent
    -0.29
    å°ģ
    -0.29
    gü
    -0.26
    èµĦæºIJéħįç½®
    -0.26
    oves
    -0.25
    sat
    -0.25
    Sent
    -0.25
    çķĻä¸ĭæĿ¥
    -0.25
    enta
    -0.25
    被æįķ
    -0.24
    POSITIVE LOGITS
    æıIJ
    0.27
    Ath
    0.26
     lo
    0.26
    ỳ
    0.25
    å®´
    0.25
    ç¾İæ´²
    0.24
     Wimbledon
    0.24
    ì
    0.24
    isk
    0.23
    (proc
    0.23
    Activations Density 0.010%

    No Known Activations