© 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. 11-RESID-POST-AA
    6. 2189
    Prev
    Next
    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     website
    -0.07
     butcher
    -0.07
    ')));↵
    -0.07
     MX
    -0.07
    łuż
    -0.07
    ﹗
    -0.07
    윱
    -0.07
    $log
    -0.07
    >
    -0.07
    ')):↵
    -0.07
    POSITIVE LOGITS
     didSet
    0.07
    _Load
    0.07
    ประเม
    0.07
    �
    0.06
     Garc
    0.06
     adoption
    0.06
     cus
    0.06
    stüt
    0.06
    .imgur
    0.06
    .errors
    0.06
    Activations Density 0.009%

    No Known Activations