© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    autumn/fall

    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
    infeld
    -0.27
    ä¸įæ¸ħ
    -0.26
    emploi
    -0.25
    èĪªæµ·
    -0.25
    .backends
    -0.24
    jem
    -0.24
    ker
    -0.24
    -playing
    -0.24
    avit
    -0.23
    ayers
    -0.23
    POSITIVE LOGITS
    uces
    0.24
     sens
    0.23
    æļijåģĩ
    0.22
    éĻį临
    0.22
     statistics
    0.22
    istik
    0.22
    vince
    0.22
    ìĭ¶
    0.22
     counselor
    0.22
    drops
    0.21
    Activations Density 0.904%

    No Known Activations