Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 89021
    Prev
    Next
    INDEX
    Explanations

    Email

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ຂ
    -0.08
    觋
    -0.07
    ゎ
    -0.07
    诹
    -0.07
    (panel
    -0.07
    劄
    -0.07
    .parts
    -0.07
     Advent
    -0.07
     истор
    -0.07
     trú
    -0.07
    POSITIVE LOGITS
     infinitely
    0.08
    さえ
    0.07
     distinctly
    0.07
    Yang
    0.07
     aggregates
    0.07
     debris
    0.07
     clich
    0.07
    ificantly
    0.07
    Steven
    0.07
     furthermore
    0.07
    Activations Density 0.005%

    No Known Activations