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. 30167
    Prev
    Next
    INDEX
    Explanations

    for

    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
     misunderstanding
    -0.07
    interpret
    -0.07
    鸤
    -0.07
    .square
    -0.06
    	matrix
    -0.06
    .split
    -0.06
    -toolbar
    -0.06
    ("*
    -0.06
     Spar
    -0.06
    並同意
    -0.06
    POSITIVE LOGITS
    훌
    0.07
    كهرباء
    0.07
     ky
    0.07
    .lb
    0.07
    Ul
    0.07
     nour
    0.07
    뜨
    0.07
    护照
    0.07
    shima
    0.07
    /Form
    0.07
    Activations Density 0.016%

    No Known Activations