© 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. 23-RESID-POST-AA
    6. 129863
    Prev
    Next
    INDEX
    Explanations

    ?

    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
    aptops
    -0.07
    слож
    -0.07
    Senha
    -0.07
    .s
    -0.07
    ผ
    -0.07
    cling
    -0.07
    绿水青山
    -0.07
    𨚕
    -0.06
    太过
    -0.06
    connexion
    -0.06
    POSITIVE LOGITS
     bast
    0.08
    斡
    0.07
    歼
    0.07
    (Abstract
    0.06
    أهم
    0.06
     representatives
    0.06
     autres
    0.06
     vardı
    0.06
     SCAN
    0.06
     OCR
    0.06
    Activations Density 0.053%

    No Known Activations