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. 19-RESID-POST-AA
    6. 2929
    Prev
    Next
    INDEX
    Explanations

    code and website content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fortunate
    -0.08
    raig
    -0.07
     gently
    -0.07
     בלבד
    -0.07
    gado
    -0.07
    ひ
    -0.07
     showError
    -0.07
    רום
    -0.07
     didFinish
    -0.07
     UNIQUE
    -0.07
    POSITIVE LOGITS
    _Block
    0.07
     Feb
    0.06
    (links
    0.06
     XXX
    0.06
    fontSize
    0.06
    publisher
    0.06
    经商
    0.06
    [list
    0.06
    建筑业
    0.06
    	style
    0.06
    Activations Density 0.199%

    No Known Activations