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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161621
    Prev
    Next
    INDEX
    Explanations

    on

    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
    èŀįåªĴä½ĵ
    -0.25
    èħ¹
    -0.24
    ta
    -0.23
    oire
    -0.23
     heraus
    -0.23
     enforce
    -0.23
     CLAIM
    -0.23
    æ¯ı个
    -0.22
    +j
    -0.22
     excl
    -0.22
    POSITIVE LOGITS
    enerate
    0.32
     trials
    0.31
     trial
    0.31
    _trials
    0.30
    pped
    0.27
    änd
    0.26
    å®ļçĤ¹
    0.26
     Trial
    0.26
    -generation
    0.26
    esen
    0.25
    Activations Density 0.010%

    No Known Activations