© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 5804
    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
     commit
    -0.07
     Olive
    -0.07
     Á
    -0.07
    Inspectable
    -0.07
     memcmp
    -0.07
    $http
    -0.07
    周恩
    -0.07
     "></
    -0.07
    converted
    -0.07
    一抹
    -0.06
    POSITIVE LOGITS
     FactoryGirl
    0.08
    RICS
    0.07
    ])),↵
    0.07
    sha
    0.06
    icking
    0.06
    婍
    0.06
    结果显示
    0.06
     Dallas
    0.06
     closed
    0.06
    .Checked
    0.06
    Activations Density 0.002%

    No Known Activations