© 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. 5803
    Prev
    Next
    INDEX
    Explanations

    Sentence fragments/general English

    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
     Reject
    -0.27
    ä¸įçĶĺ
    -0.26
     Plenty
    -0.25
    #=
    -0.25
    rike
    -0.24
    ha
    -0.24
    -sizing
    -0.24
    å¾Īå¤ļäºĭæĥħ
    -0.24
    éĻ©
    -0.24
    elper
    -0.24
    POSITIVE LOGITS
    itim
    0.28
    ÑĥлÑĮ
    0.27
    orrh
    0.26
    OWN
    0.25
    çİĩè¾¾åĪ°
    0.25
     tend
    0.25
    _GU
    0.24
    addWidget
    0.24
    łéĻ¤
    0.24
    anford
    0.24
    Activations Density 0.027%

    No Known Activations