© 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. 163454
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    .TabStop
    -0.26
    ï¬Ģ
    -0.25
    é¡¿
    -0.25
    è§Ħ模以ä¸Ĭ
    -0.25
    uffers
    -0.24
    ÑĤе
    -0.24
    eref
    -0.24
    .cgi
    -0.24
    带头人
    -0.23
    te
    -0.23
    POSITIVE LOGITS
    SCP
    0.31
    REA
    0.31
    zsche
    0.25
     Rex
    0.25
    Unsupported
    0.25
     bypass
    0.24
     sandwiches
    0.23
    lobe
    0.23
     turb
    0.23
    åħ±åĴĮ
    0.23
    Activations Density 0.004%

    No Known Activations