© 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. 11-RESID-POST-AA
    6. 92159
    Prev
    Next
    INDEX
    Explanations

    passage excerpts

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.07
                             
    -0.07
    vk
    -0.06
    					    
    -0.06
    ichage
    -0.06
     thẻ
    -0.06
    Rem
    -0.06
    数据显示
    -0.06
    𓂃
    -0.06
    astically
    -0.06
    POSITIVE LOGITS
     Union
    0.08
     Tow
    0.07
     Sculpt
    0.07
     Automatically
    0.07
    слуш
    0.07
     tunnel
    0.07
     Smithsonian
    0.07
     IPCC
    0.07
    _uv
    0.06
     Hoover
    0.06
    Activations Density 0.125%

    No Known Activations