© 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. 23-TRANSCODER-HP
    7. 162290
    Prev
    Next
    INDEX
    Explanations

    Beginning of sentence/fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &S
    -0.31
     B
    -0.27
     dec
    -0.26
    è¯į
    -0.26
     SU
    -0.25
    Async
    -0.25
     indent
    -0.25
    &M
    -0.25
    ä¸İä¸ŃåĽ½
    -0.24
     compat
    -0.24
    POSITIVE LOGITS
    åįĬ个å°ıæŶ
    0.26
    ãĥ©ãĥ³ãĥī
    0.24
    orney
    0.23
    otos
    0.23
    atts
    0.23
    lands
    0.23
    formance
    0.23
    éĴ»çŁ³
    0.23
     Politico
    0.23
    urance
    0.23
    Activations Density 0.014%

    No Known Activations