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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 31454
    Prev
    Next
    INDEX
    Explanations

    code/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
    היינו
    -0.07
    month
    -0.07
     Presidents
    -0.06
    ",$
    -0.06
     plaintiff
    -0.06
     уме
    -0.06
     energía
    -0.06
     spouse
    -0.06
    ועד
    -0.06
    _combine
    -0.06
    POSITIVE LOGITS
    拦截
    0.07
    sm
    0.07
     checks
    0.07
     sift
    0.07
     크
    0.07
    縢
    0.06
    읿
    0.06
     mar
    0.06
    눴
    0.06
    朵
    0.06
    Activations Density 0.008%

    No Known Activations