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. 15-RESID-POST-AA
    6. 45715
    Prev
    Next
    INDEX
    Explanations

    syntax symbol

    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
     Phase
    -0.07
    _chunk
    -0.07
     Barnes
    -0.07
     لديه
    -0.07
     ты
    -0.07
     dentro
    -0.07
    原则上
    -0.07
    减弱
    -0.07
    .states
    -0.07
     Ninja
    -0.07
    POSITIVE LOGITS
     CONSTANT
    0.07
    	system
    0.07
    UIAlert
    0.07
     esteem
    0.07
    無しさん
    0.06
    _SUBJECT
    0.06
     Гор
    0.06
     sew
    0.06
    sidebar
    0.06
     corrosion
    0.06
    Activations Density 0.004%

    No Known Activations