© 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. 42245
    Prev
    Next
    INDEX
    Explanations

    Romania

    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
     TKey
    -0.08
    亥
    -0.08
    group
    -0.08
    /service
    -0.08
    向け
    -0.07
    XmlElement
    -0.07
    <TKey
    -0.07
     vid
    -0.07
     fert
    -0.07
    غض
    -0.07
    POSITIVE LOGITS
    ">(
    0.07
    _notes
    0.07
    舯
    0.06
     młod
    0.06
     shells
    0.06
    了一
    0.06
     hành
    0.06
    PlainOldData
    0.06
     Scor
    0.06
    emales
    0.06
    Activations Density 0.003%

    No Known Activations