© 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. 54268
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Cre
    -0.28
     Anch
    -0.28
    .dr
    -0.25
    æķ°åĢ¼
    -0.25
     dr
    -0.25
     dout
    -0.24
    пло
    -0.24
     Liv
    -0.24
     Di
    -0.24
    _DR
    -0.23
    POSITIVE LOGITS
    jack
    0.28
    LEASE
    0.28
    å¸ĿåĽ½
    0.27
    çĶŁäº§åĴĮ
    0.25
    åĨħåĪĨæ³Į
    0.24
    åħļ
    0.24
     secre
    0.24
    ubic
    0.24
     screams
    0.24
    å½±
    0.23
    Activations Density 0.004%

    No Known Activations