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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 85021
    Prev
    Next
    INDEX
    Explanations

    Twig templating language

    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
    _SM
    -0.10
    ทร
    -0.07
    _E
    -0.07
    Design
    -0.07
    �
    -0.07
    Av
    -0.06
    Industry
    -0.06
     Austral
    -0.06
    Ev
    -0.06
    -vs
    -0.06
    POSITIVE LOGITS
     adjustment
    0.08
    避开
    0.07
     ];↵
    0.07
     padded
    0.07
     nest
    0.07
    .Parser
    0.07
    licer
    0.07
     Rex
    0.06
    бед
    0.06
    季后
    0.06
    Activations Density 0.014%

    No Known Activations