© 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. 19-TRANSCODER-HP
    7. 9234
    Prev
    Next
    INDEX
    Explanations

    una

    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
    open
    -0.27
    gon
    -0.27
    dyn
    -0.26
    onz
    -0.26
    onic
    -0.26
    注æĦıåĪ°
    -0.26
    agara
    -0.26
    æ·¼
    -0.25
    åıijçİ°äºĨ
    -0.25
     open
    -0.25
    POSITIVE LOGITS
    æĺ¥é£İ
    0.28
     ApiException
    0.28
    æ¯į
    0.25
    çĸijéļ¾
    0.25
     Hubb
    0.25
    apeut
    0.24
    åĵĪå°Ķ
    0.24
    createView
    0.24
    privileged
    0.24
    -major
    0.24
    Activations Density 0.028%

    No Known Activations