© 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. 111183
    Prev
    Next
    INDEX
    Explanations

    smoking

    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
    element
    -0.09
     Nome
    -0.08
    razier
    -0.08
     cz
    -0.07
    WithString
    -0.07
    חס
    -0.07
    ierrez
    -0.07
     Astr
    -0.07
     Assess
    -0.07
     differently
    -0.07
    POSITIVE LOGITS
    فات
    0.08
    работка
    0.08
    שיווק
    0.08
    隔音
    0.07
    .emplace
    0.07
     killings
    0.07
    .fillText
    0.07
     '\
    0.07
     ;)↵↵
    0.07
    	debug
    0.07
    Activations Density 0.010%

    No Known Activations