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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5720
    Prev
    Next
    INDEX
    Explanations

    should must

    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
    åı·
    -0.29
    noc
    -0.27
    кал
    -0.26
    èĻŁ
    -0.25
    obby
    -0.25
    ron
    -0.24
    失åİ»
    -0.24
    quete
    -0.24
    onet
    -0.23
    -badge
    -0.23
    POSITIVE LOGITS
    baugh
    0.27
    èĩ¾
    0.26
    ä¸Ī夫
    0.26
    çĶ·ä¸»
    0.25
    fic
    0.24
    æ®ĥ
    0.24
    s
    0.24
     preceded
    0.23
    XHR
    0.23
    lude
    0.23
    Activations Density 0.479%

    No Known Activations