© 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. 163400
    Prev
    Next
    INDEX
    Explanations

    of

    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
    éļıçĿĢ
    -0.26
    äºĴåĬ©
    -0.26
     implications
    -0.25
    -sur
    -0.25
    è£ħ
    -0.25
    .jquery
    -0.24
    èµ°è¿ĩ
    -0.24
    igh
    -0.24
    stem
    -0.24
     acknowledgment
    -0.24
    POSITIVE LOGITS
    %"↵
    0.26
    /from
    0.26
    è¿ĻäºĽä¸ľè¥¿
    0.26
    ParameterValue
    0.25
    è¿Ļä¸ĢçĤ¹
    0.25
    .nodeName
    0.24
    esan
    0.24
     scratch
    0.24
    lined
    0.24
    _SEGMENT
    0.24
    Activations Density 0.010%

    No Known Activations