© 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. 45228
    Prev
    Next
    INDEX
    Explanations

    License

    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
    ✍
    -0.09
    MESS
    -0.08
     IOC
    -0.08
    幹
    -0.07
    Tom
    -0.07
    浸泡
    -0.07
     cheesy
    -0.07
     artwork
    -0.07
     listItem
    -0.07
     imagePath
    -0.07
    POSITIVE LOGITS
     mounts
    0.08
    Reason
    0.07
    :“
    0.07
     difficulty
    0.07
     objective
    0.07
    >Show
    0.07
    lyn
    0.06
    假
    0.06
    빪
    0.06
    .Interval
    0.06
    Activations Density 0.004%

    No Known Activations