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. 1648
    Prev
    Next
    INDEX
    Explanations

    attacks

    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
     xb
    -0.07
     impecc
    -0.07
    	start
    -0.07
     last
    -0.07
    	old
    -0.07
    指
    -0.06
     maintained
    -0.06
    aporan
    -0.06
    弟
    -0.06
    ⽉
    -0.06
    POSITIVE LOGITS
     Müsl
    0.07
     Bis
    0.07
    .WinForms
    0.07
    setFlash
    0.07
    棤
    0.07
    �
    0.07
    Ctl
    0.07
    альных
    0.07
    רית
    0.07
    颁布
    0.07
    Activations Density 0.037%

    No Known Activations