© 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. 23856
    Prev
    Next
    INDEX
    Explanations

    Academic subjects

    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
    eldon
    -0.08
    Weak
    -0.08
    春秋
    -0.07
     rising
    -0.06
    �
    -0.06
    קלאסי
    -0.06
    有利于
    -0.06
    הולך
    -0.06
    _alt
    -0.06
     magnetic
    -0.06
    POSITIVE LOGITS
     hài
    0.07
    流泪
    0.07
    company
    0.07
    白色的
    0.07
    𝑟
    0.06
    our
    0.06
    附加
    0.06
    getRequest
    0.06
    笑话
    0.06
    rai
    0.06
    Activations Density 0.025%

    No Known Activations