© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    6. 86229
    Prev
    Next
    INDEX
    Explanations

    =

    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
     CCS
    -0.07
    *u
    -0.07
    ทำความ
    -0.07
    different
    -0.07
     undercut
    -0.07
    alley
    -0.07
     StringField
    -0.07
    MAP
    -0.07
    _MD
    -0.07
     Notes
    -0.06
    POSITIVE LOGITS
    ahir
    0.08
    يت
    0.07
    שים
    0.07
    ']
    0.07
    ():
    0.06
    每次
    0.06
    ////↵
    0.06
    ści
    0.06
    不起
    0.06
     tối
    0.06
    Activations Density 0.003%

    No Known Activations