© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    6. 57104
    Prev
    Next
    INDEX
    Explanations

    browning

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hükü
    -0.07
     simd
    -0.06
    .tell
    -0.06
    (assigns
    -0.06
    :error
    -0.06
    ⍲
    -0.06
     abyss
    -0.06
    דוד
    -0.06
     RequestOptions
    -0.06
    kir
    -0.06
    POSITIVE LOGITS
     PG
    0.07
     durable
    0.07
    应当
    0.07
    日常
    0.07
    晏
    0.06
     Detailed
    0.06
    霉素
    0.06
    ****************************************
    0.06
    _BASIC
    0.06
    Widget
    0.06
    Activations Density 0.001%

    No Known Activations