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. 120751
    Prev
    Next
    INDEX
    Explanations

    splitter

    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
    له
    -0.07
     h
    -0.07
                                     
    -0.06
    ес
    -0.06
     operatives
    -0.06
    vie
    -0.06
    »
    -0.06
    тон
    -0.06
    /"↵
    -0.06
    "]↵↵
    -0.06
    POSITIVE LOGITS
     disturb
    0.08
     ביחד
    0.07
     NEW
    0.07
     beim
    0.07
     Firmware
    0.07
     awarded
    0.07
    OfWeek
    0.07
    .chunk
    0.07
    stüt
    0.06
     Presents
    0.06
    Activations Density 0.015%

    No Known Activations