© 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. 116826
    Prev
    Next
    INDEX
    Explanations

    multim

    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
     frag
    -0.07
    の大
    -0.07
    mall
    -0.07
    иг
    -0.06
     hugs
    -0.06
    晏
    -0.06
    Font
    -0.06
    咆
    -0.06
    "|
    -0.06
    .Export
    -0.06
    POSITIVE LOGITS
     noticed
    0.07
    ,L
    0.06
     kald
    0.06
    	CString
    0.06
    近
    0.06
    clidean
    0.06
    isempty
    0.06
     }));↵
    0.06
    asad
    0.06
     setC
    0.06
    Activations Density 0.103%

    No Known Activations