© 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. 123201
    Prev
    Next
    INDEX
    Explanations

    score

    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
    Men
    -0.07
     Developing
    -0.07
    	es
    -0.07
     signin
    -0.07
    发展趋势
    -0.07
    .CreateTable
    -0.06
    Faculty
    -0.06
    微商
    -0.06
    𝐜
    -0.06
    𝖒
    -0.06
    POSITIVE LOGITS
     FileInfo
    0.07
    .other
    0.07
    ったら
    0.07
     лит
    0.07
    ivil
    0.06
     bare
    0.06
     Mitgli
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    (float
    0.06
     grounding
    0.06
    Activations Density 0.009%

    No Known Activations