© 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. 53735
    Prev
    Next
    INDEX
    Explanations

    death related texts

    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
    æŃ»åİ»
    -0.31
     Kill
    -0.30
    éĽħ
    -0.27
    æŃ»
    -0.27
    kills
    -0.27
    ames
    -0.27
    ä¸ĭæĿ¥
    -0.26
    аниз
    -0.25
    htags
    -0.25
    ниÑĨÑĭ
    -0.25
    POSITIVE LOGITS
    å¾·
    0.32
     departing
    0.31
     ban
    0.29
    à¸Ķ
    0.28
     ann
    0.28
    ëį°
    0.28
    å¾
    0.28
    ä½ĵèĤ²
    0.28
    DE
    0.27
    èĦ±
    0.27
    Activations Density 0.014%

    No Known Activations