© 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. 53590
    Prev
    Next
    INDEX
    Explanations

    giving advice

    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
     Should
    -0.72
    should
    -0.68
    Should
    -0.67
     should
    -0.65
     shouldn
    -0.60
    åºĶ
    -0.60
    åºĶ该
    -0.58
    æĩī
    -0.58
    .Should
    -0.56
    _should
    -0.56
    POSITIVE LOGITS
    åı¸
    0.28
    åŁł
    0.26
    orus
    0.25
     Decomp
    0.25
    san
    0.25
    stile
    0.24
    eled
    0.24
    bor
    0.23
    çŃīçī¹çĤ¹
    0.23
    icional
    0.23
    Activations Density 0.098%

    No Known Activations