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. 24685
    Prev
    Next
    INDEX
    Explanations

    Cooking instructions

    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
     fetch
    -0.08
     CONCAT
    -0.08
    Toast
    -0.07
     Flames
    -0.07
     isAdmin
    -0.07
    疮
    -0.07
     lesions
    -0.07
    Decrypt
    -0.07
    iotics
    -0.07
    湓
    -0.07
    POSITIVE LOGITS
    HER
    0.08
     kra
    0.07
     race
    0.07
    שירות
    0.07
    ')";↵
    0.07
    نظر
    0.07
    ЛО
    0.06
     ********************************
    0.06
    ɯ
    0.06
     arbe
    0.06
    Activations Density 0.017%

    No Known Activations