© 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. 54396
    Prev
    Next
    INDEX
    Explanations

    code and technical discussions

    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
    è¿Ļ件äºĭæĥħ
    -0.46
    éĥ½èĥ½å¤Ł
    -0.40
    éĤ£ä¸ªæŶåĢĻ
    -0.37
    ä»Ģä¹Īäºĭæĥħ
    -0.37
    å°±èĥ½å¤Ł
    -0.36
    ä¸įä»ħä»ħ
    -0.36
    æĽ´åĬł
    -0.36
    åıĺå¾ĹæĽ´åĬł
    -0.36
    ä¸įä»ħåı¯ä»¥
    -0.35
    åįłæį®äºĨ
    -0.35
    POSITIVE LOGITS
     specs
    0.30
     teens
    0.29
    åĴ±
    0.28
     IPs
    0.28
    /wiki
    0.28
     basics
    0.28
     vs
    0.28
    tics
    0.27
     overlap
    0.27
    计
    0.27
    Activations Density 0.018%

    No Known Activations