Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 21467
    Prev
    Next
    INDEX
    Explanations

    out

    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
     escort
    -0.07
    🍫
    -0.07
     Allow
    -0.06
    OrNil
    -0.06
     caffe
    -0.06
    	ss
    -0.06
    重构
    -0.06
    🚌
    -0.06
    ألوان
    -0.06
    Perm
    -0.06
    POSITIVE LOGITS
    .choice
    0.07
     gobierno
    0.07
     uom
    0.07
     Campos
    0.07
    essoa
    0.07
    /go
    0.07
     lawn
    0.07
     Kuwait
    0.07
    .Printf
    0.06
    明
    0.06
    Activations Density 0.001%

    No Known Activations