© 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. 15-RESID-POST-AA
    6. 116618
    Prev
    Next
    INDEX
    Explanations

    adequate amount

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ımı
    -0.07
    izzes
    -0.07
     Retreat
    -0.07
     reordered
    -0.07
    ippets
    -0.07
     hdc
    -0.07
    _flow
    -0.07
     neighboring
    -0.07
     Disorders
    -0.06
    唯美
    -0.06
    POSITIVE LOGITS
    atherine
    0.08
    .reloadData
    0.08
     Dhabi
    0.07
    真的很
    0.07
    _aut
    0.07
     sede
    0.06
    getView
    0.06
    邓
    0.06
    .Transport
    0.06
    惊叹
    0.06
    Activations Density 0.047%

    No Known Activations