© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    public

    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
    ä¸įåħĭ
    -0.28
    igion
    -0.28
     sight
    -0.27
    tl
    -0.27
     inclusive
    -0.26
    ntl
    -0.26
    inclusive
    -0.25
    scape
    -0.24
    "user
    -0.24
     wre
    -0.24
    POSITIVE LOGITS
    äºĪ以
    0.28
    便åı¯
    0.28
     sodom
    0.28
    åĶ¯ä¸Ģ
    0.28
    _marshall
    0.27
    -share
    0.26
    åį³åı¯
    0.26
    åħħ
    0.26
     share
    0.25
     SharedPreferences
    0.25
    Activations Density 0.022%

    No Known Activations