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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-RESID-POST-AA
    6. 130733
    Prev
    Next
    INDEX
    Explanations

    economy

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungal
    -0.07
    Attend
    -0.07
     twisting
    -0.07
     insight
    -0.07
    _docs
    -0.07
    Ka
    -0.07
    眼看
    -0.07
     poison
    -0.07
    ewear
    -0.06
    믾
    -0.06
    POSITIVE LOGITS
    �
    0.07
     bols
    0.07
    英特
    0.07
    .cm
    0.07
    減
    0.07
     RequestMethod
    0.07
     مجل
    0.07
    imps
    0.07
    계획
    0.07
    enchmark
    0.07
    Activations Density 0.020%

    No Known Activations