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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 30108
    Prev
    Next
    INDEX
    Explanations

    make

    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
    ",__
    -0.07
    _AUTO
    -0.07
     animals
    -0.07
     الاتحاد
    -0.07
    graphic
    -0.07
     государственн
    -0.07
    氚
    -0.07
     triển
    -0.07
    ographical
    -0.07
    iscal
    -0.07
    POSITIVE LOGITS
     shortcuts
    0.07
     hundred
    0.07
     THREE
    0.07
     Coast
    0.07
    _packages
    0.07
    Numer
    0.07
     stealing
    0.07
    .ToArray
    0.07
     Honda
    0.06
    _inputs
    0.06
    Activations Density 0.029%

    No Known Activations