© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7450
    Prev
    Next
    INDEX
    Explanations

    Negative or problematic topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inia
    -0.31
     roc
    -0.31
    criptive
    -0.29
     streak
    -0.26
    ropic
    -0.25
    roc
    -0.25
    cient
    -0.24
    çĥŃæ½®
    -0.24
    obic
    -0.23
     ÑģÑĢазÑĥ
    -0.23
    POSITIVE LOGITS
    flate
    0.29
    èĢ³
    0.27
    æł¡
    0.25
    -parts
    0.24
    -upper
    0.24
    ç³ħ
    0.23
    /****************
    0.23
     part
    0.23
    æŃĨ
    0.23
    зеÑĢ
    0.23
    Activations Density 0.094%

    No Known Activations