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. 2450
    Prev
    Next
    INDEX
    Explanations

    playing cards

    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
     Trotsky
    -0.09
     Bau
    -0.08
    Ā
    -0.08
     José
    -0.07
     ngu
    -0.07
    �
    -0.07
     junto
    -0.07
     Marl
    -0.07
    不明白
    -0.07
     ansible
    -0.07
    POSITIVE LOGITS
     FILTER
    0.07
     PB
    0.07
    DEN
    0.07
     Variant
    0.07
     RED
    0.07
    丁
    0.06
    ACHER
    0.06
     Imports
    0.06
    filter
    0.06
    setName
    0.06
    Activations Density 0.010%

    No Known Activations