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. 23-RESID-POST-AA
    6. 130114
    Prev
    Next
    INDEX
    Explanations

    ESG and sustainability reports

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    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
     å
    -0.08
    .calc
    -0.08
     Carlton
    -0.08
    种类
    -0.07
                                    
    -0.07
     für
    -0.07
    顆
    -0.07
     versch
    -0.07
    '%(
    -0.07
     aantal
    -0.07
    POSITIVE LOGITS
     ride
    0.07
    柄
    0.07
    👁
    0.07
     bead
    0.06
    Quote
    0.06
    hook
    0.06
     vines
    0.06
    血腥
    0.06
    roperty
    0.06
    ড
    0.06
    Activations Density 0.115%

    No Known Activations