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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88030
    Prev
    Next
    INDEX
    Explanations

    ">"

    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
    英勇
    -0.07
    柝
    -0.07
    .Visual
    -0.07
     violet
    -0.06
     Csv
    -0.06
    >C
    -0.06
    חשב
    -0.06
     jeszcze
    -0.06
    .setHorizontal
    -0.06
    sons
    -0.06
    POSITIVE LOGITS
     apology
    0.08
    Plot
    0.08
    '}↵
    0.07
    ‘s
    0.07
    师父
    0.07
    -password
    0.07
    参数
    0.07
    Loss
    0.07
     '.$
    0.06
    走路
    0.06
    Activations Density 0.002%

    No Known Activations